XekRung Technical Report
Listen
Radio episode about this paper
Transcript
Introduction to the show: ident: Security Radio. Generated commentary on the latest security and cryptography papers.
Nadia: We're looking at the paper: "XekRung Technical Report".
Elias: Here's the gist of the paper. XekRung is a frontier large language model for cybersecurity designed to provide comprehensive security capabilities by developing diverse data synthesis pipelines and a complete training pipeline spanning continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL) <ref:2605.00072#pg2>.
Nadia: Model Performance and Benchmarking XekRung achieves state-of-the-art performance on cybersecurity benchmarks among models of the same scale, while maintaining strong performance on general benchmarks <ref:2605.00072#pg2>.
Elias: The overall average score for XekRung-8B across 15 cybersecurity benchmarks is 81.04% <ref:2605.00072#pg2>.
Nadia: This represents a +9.03 percentage point improvement over its base model Qwen3-8B (72.01%) and surpasses all same-scale baselines by a substantial margin <ref:2605.00072#pg2>.
Title and authors: Nadia: Let's talk about the title and who wrote this, the XekRung Technical Report. It sets up what we are looking at—a large language model built for cybersecurity that aims to give it comprehensive security capabilities.
Elias: The authors are Jiutian Zeng, Junjie Li, Chengwei Dai, Jie Liang, Zhaoyu Hu, Yiliang Zhang, Ziang Weng, and Longtao Huang as core contributors. They seem to have a strong mix of expertise here.
Priya: I noticed the team includes people focused on different parts of the problem—from measurement research to exploitation and defense. That suggests they're trying to cover the whole cycle.
Nadia: Right, because what they're doing is tackling something inherently cross-domain and cross-layer, which means you need mastery over software engineering, operating systems, network protocols, and cryptographic primitives all at once.
Elias: The paper also points out that the search space in cybersecurity is vast because adversarial behaviors can show up across an enormous landscape of possible configurations and execution paths that just makes exhaustive enumeration infeasible.
Priya: That sounds like a huge hurdle for any system trying to learn this, so I'm curious if their data strategies really help navigate that complexity.
The paper's summary: Nadia: Now let's look at what the report actually summarizes about XekRung. Basically, they show that XekRung achieves state-of-the-art performance on cybersecurity benchmarks compared to other models of the same scale, while still keeping strong performance on general tasks.
Elias: The key number here is that the average score across fifteen cybersecurity benchmarks for XekRung-8B is eighty-one point zero four percent, which they say is a nine point zero three percentage point improvement over its base model, Qwen3-8B, which scored seventy-two point zero one percent.
Priya: eighty-one point zero four percent on those specific security metrics sounds pretty solid for a specialized model, but I need to know what that means in terms of real utility versus just high scores on a test set.
Nadia: It means it outperforms all the same-scale baselines by a substantial margin, and critically, XekRung-8B still holds seventy-two point five four percent overall on general purpose benchmarks, which is close to the base Qwen3-8B's seventy-three point thirty one percent.
Elias: That comparison shows that they managed to get deep domain expertise without completely losing general competence, which is a tough balance to strike in these specialized training efforts.
The paper's improvements: Nadia: The report highlights the specific ways they improved the model's capabilities. They built a system spanning continued pre-training, supervised fine-tuning, and reinforcement learning to extend the model’s abilities across tasks.
Elias: They introduce a multi-dimensional evaluation system that guides iterative improvement for both domain-specific and general purpose abilities throughout the whole training process.
Priya: I'm interested in how they structured that RL part because traditional RL often targets isolated subtasks, but this one seems to aim for something more unified.
Nadia: They move away from targeting just isolated subtasks by introducing a framework that unifies reinforcement learning with verifiable rewards, which we call Verifiable Rewards or RLVR for those specific tasks.
Elias: Plus, they use Agentic RL for end-to-end workflow optimization and they integrate reasoning reinforcement learning with preference alignment within a shared optimization loop.
Priya: That sounds like it’s trying to optimize the entire chain of security analysis, not just one step in it. How does that translate to actual capability?
Conclusion: Nadia: To wrap things up on this XekRung Technical Report, the main implication is that a well-trained 8B model can match or even exceed models with several times more parameters when it comes to domain-specific security tasks.
Elias: That highlights how effective domain compression can be, showing that deep expertise in a smaller model can outperform much larger models on specialized problems.
Priya: I just want to stress that the authors mention they are planning to further expand the model’s agentic capabilities and look into self-evolution for cybersecurity applications next.
Nadia: Right, so while this report shows strong performance, the team is focused on making it more capable of actually *doing* things autonomously in a security context.
Elias: They also plan to pursue broader cybersecurity research and applications based on this work, continuing the development of AI for Security.
Alibaba Security AGI Lab
cs.CR, cs.AI
Submitted: 2026-04-30
Updated: 2026-11-06
Comments: 23 pages, 2 figures, 5 tables. Jiutian Zeng, Junjie Li, Chengwei Dai, Jie Liang, and Zhaoyu Hu contributed equally to this work
Code: https://github.com/XuanwuAI/SecEval
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
Importance score: 100/100
The gist: XekRung is a frontier large language model for cybersecurity designed to provide comprehensive security capabilities by developing diverse data synthesis pipelines and a complete training pipeline…
Key concepts
- Full Training Pipeline (CPT→SFT→RL)
- This is a complete, three-stage training process: Continued Pre-Training (CPT) builds foundational knowledge on cybersecurity concepts; Supervised Fine-Tuning (SFT) teaches the model specific security tasks; and Reinforcement Learning (RL) refines behavior through trial and error. This ensures the model learns both general language skills and deep, specialized security expertise.
- Group Relative Policy Optimization (GRPO)
- GRPO is a specific type of multi-task reinforcement learning used during the training phase. It allows the model to optimize its performance across many different security tasks simultaneously by comparing its actions against a group of related policies. This helps the model learn robust strategies for various security scenarios efficiently.
- Agentic RL and ActionRL
- These concepts enable the model to act like an autonomous agent in complex workflows. Agentic RL optimizes end-to-end operational tasks, while ActionRL specifically focuses supervision on critical decision points, known as the 'Branch Divergence Point,' ensuring the model makes precise, effective moves during security analysis.
Terminology
Summary
XekRung is a frontier large language model for cybersecurity designed to provide comprehensive security capabilities by developing diverse data synthesis pipelines and a complete training pipeline spanning continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL) <ref:2605. p. 0 To achieve this, we develop diverse
data synthesis pipelines tailored to the cybersecurity domain, enabling the scalable
construction of high-quality training data and providing a strong foundation for
cybersecurity knowledge and understanding. Building on this foundation, we establish
a complete training pipeline spanning continued pre-training (CPT), supervised
fine-tuning (SFT), and reinforcement learning (RL) to further extend the model’s
capabilities.Where the paper says it
Model Performance and Benchmarking
XekRung achieves state-of-the-art performance on cybersecurity benchmarks among models of the same scale, while maintaining strong performance on general benchmarks <ref:2605.00072#pg2>. The overall average score for XekRung-8B across 15 cybersecurity benchmarks is 81. p. 0 Extensive
experiments demonstrate that XekRung achieves state-of-the-art performance on
cybersecurity-specific benchmarks among models of the same scale, while maintaining
strong performance on general benchmarks. Overall Average Score
15 Benchmarks Average across cybersecurity benchmarks
CSEBench · CTIBench-MCQ/RCM/VSP/ATE · MMLU-CompSec · SecEval · SecBench-MCQ · CyberMetric10kQ/2kQ/500Q/80Q · CISSP-MC-ZH/SC-EN/SC-ZH
Qwen3-8B Qwen3-14B Qwen3. XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605. 04% across all 15 security benchmarks, representing a +9. 03 percentage
point improvement over its base model Qwen3-8B (72. 03 percentage
point improvement over its base model Qwen3-8B (72. 01%) and surpassing all same-scale baselines by a
substantial margin—including Foundation-Sec-8B-Reasoning (68. 21%) by over 12 percentage points on domain tasks. Crucially,
these domain gains come with minimal degradation of general capabilities: XekRung-8B retains 72. Crucially,
these domain gains come with minimal degradation of general capabilities: XekRung-8B retains 72. 54%
overall on general-purpose benchmarks, closely tracking the base Qwen3-8B (73. XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Data Engineering and Synthesis Strategies
The authors built a data engineering system spanning the entire training lifecycle, combining learned quality scoring, capability-level interference balancing, and vector-space deduplication on the quality side <ref:2605.00072#pg2>. They introduced four targeted strategies to augment the corpus along the dimensions of representation, correlation, long-range dependency and engineering experience injection <ref:2605. p. 5 3 Domain-Specific Data Strategies
While the unified pipeline resolves generic data quality issues, cybersecurity corpora present several
domain-specific challenges: critical artifact types suffer from severe data sparsity; semantically related
threat intelligence is fragmented across disparate sources; and genuine long-range dependencies are
rarely captured by naive document concatenation. To address these, we introduce four targeted strategies
to augment the corpus along the dimensions of representation, correlation, long-range dependency and
engineering experience injection.Where the paper says it
-
Explanatory Annotation for Domain-Specific Artifacts <ref:2605. p. 5
00072#pg7>.Where the paper says it
To address these, we introduce four targeted strategies to augment the corpus along the dimensions of representation, correlation, long-range dependency and engineering experience injection. Explanatory Annotation for Domain-Specific Artifacts.
-
Correlated Information Aggregation. p. 5
Where the paper says it
To overcome this, we pair each raw artifact with a concise, synthetically generated natural-language explanation that articulates its semantics, security implications, and operational context, effectively transforming specialized tool outputs into self-contained, semantically rich training instances. Correlated Information Aggregation.
-
Long-Context Data Synthesis via Entropy. p. 6
Where the paper says it
, 2023), and the two can be combined. Long-Context Data Synthesis via Entropy.
-
Explicit Orchestration of Engineering Experience. p. 6
Where the paper says it
Crucially, the fundamental long-range capabilities established during this phase lay the structural foundation within the attention mechanism for processing genuine, long-horizon agent trajectories during mid-training (see § 3. Explicit Orchestration of Engineering Experience.
Complete and Innovative Training Pipeline
XekRung realizes a full CPT → SFT → RL pipeline with task-aware specialization for cybersecurity. The post-training unifies Reinforcement Learning with Verifiable Rewards (RLVR) for verifiable-reward tasks and Agentic RL for end-to-end workflow optimization. p. 2 XekRung realizes a full CPT → SFT → RL pipeline with
task-aware specialization for cybersecurity. Post-training unifies Reinforcement Learning with Verifiable
Rewards (RLVR) for verifiable-reward tasks and Agentic RL for end-to-end workflow optimization,
complemented by code-verified adversarial self-evolution and vulnerability self-play. , 2025) has demonstrated the potency of reinforcement learning for complex problem-solving, the
systematic application of RL across the full breadth of cybersecurity tasks—with their heterogeneous
reward structures, diverse task formulations, and stringent operational constraints—remains largely
underexplored. Existing efforts, where RL is employed at all, tend to target isolated subtasks rather than
pursuing a unified, multi-task RL framework capable of jointly optimizing analytical reasoning, agentic
workflows, and behavioral alignment within the security domain. Building upon this foundation, it advances to a multi-task RL phase powered by Group
Relative Policy Optimization (GRPO). Ultimately, a self-evolutionary loop grounded in verifiable code
execution ensures sustained breakthroughs in complex reasoning.Where the paper says it
Where the paper says it
Where the paper says it
Evaluation Protocol and Results
The comprehensive evaluation involves a multi-dimensional protocol covering 35 general and 15 cybersecurity-specific benchmarks. The results show that XekRung-8B outperforms both general-purpose baselines and security-specialized baselines across both benchmark suites. p. 0 04
≈57
Figure 1: Overview of XekRung’s performance across 15 cybersecurity benchmarks compared with
general-purpose frontier models and existing security-specialized models. XekRung achieves leading
results on all evaluated dimensions. 03 percentage
point improvement over its base model Qwen3-8B (72. 01%) and surpassing all same-scale baselines by a
substantial margin—including Foundation-Sec-8B-Reasoning (68. 3-70B-Instruct Llama-Primus-Reasoning-8B
Foundation-Sec-8B-Reasoning SecGPT-14B XekRung-8B
72. 04
≈57
Figure 1: Overview of XekRung’s performance across 15 cybersecurity benchmarks compared with
general-purpose frontier models and existing security-specialized models.Where the paper says it
Where the paper says it
Where the paper says it
Scaling Implications
XekRung achieves competitive or superior performance relative to Qwen3-14B (nearly 2× the parameter count) across several benchmark categories. XekRung-8B also outperforms the larger SecGPT-14B on security benchmarks by a significant margin (81. p. 0 3-70B-Instruct Llama-Primus-Reasoning-8B
Foundation-Sec-8B-Reasoning SecGPT-14B XekRung-8B
72. 04
≈57
Figure 1: Overview of XekRung’s performance across 15 cybersecurity benchmarks compared with
general-purpose frontier models and existing security-specialized models. Extensive
experiments demonstrate that XekRung achieves state-of-the-art performance on
cybersecurity-specific benchmarks among models of the same scale, while maintaining
strong performance on general benchmarks. Overall Average Score
15 Benchmarks Average across cybersecurity benchmarks
CSEBench · CTIBench-MCQ/RCM/VSP/ATE · MMLU-CompSec · SecEval · SecBench-MCQ · CyberMetric10kQ/2kQ/500Q/80Q · CISSP-MC-ZH/SC-EN/SC-ZH
Qwen3-8B Qwen3-14B Qwen3. We systematize evaluation into a multi-dimensional protocol covering
35 general and 15 cybersecurity-specific benchmarks, jointly assessing domain proficiency and generalcapability retention to resist narrow-task overfitting. XekRung-8B achieves state-of-the-art security
performance among same-scale models while competing with several-times-larger models in nonthinking mode with exceptional token efficiency. The final mixture is selected by jointly considering domain performance, general-capability retention,
and training stability rather than any single metric. Overall, we follow the mixing principle of preserving
general competence while strengthening cybersecurity expertise, enabling the model to substantially
absorb domain knowledge without materially sacrificing its general understanding and reasoning ability.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Conclusion
In this technical report, we introduce XekRung, a frontier large language model tailored for the cybersecurity. The authors plan to further expand the model’s agentic capabilities and investigate the potential of self-evolution for cybersecurity. p. 2 To bridge the gap between surface-level knowledge and deep operational understanding (the core
limitation of general-purpose models identified above), we devise domain-aware data construction
and synthesis strategies that enrich rare yet decision-critical security concepts, model cross-artifact
dependencies, and transform opaque security artifacts into self-explanatory training instances—
collectively enabling the model to internalize the structural and causal patterns of the domain rather
than merely memorizing isolated facts. To overcome the limitations of narrow task-specific RL (the
key deficit of existing domain models), we design a unified multi-task RL framework that integrates
Reasoning RL with verifiable rewards for analytical tasks and Agentic RL for multi-step tool-augmented
operational workflows, complemented by an adversarial self-evolution mechanism for continuous
capability escalation.Where the paper says it
Authors
Core Contributors are Jiutian Zeng, Junjie Li, Chengwei Dai, Jie Liang, Zhaoyu Hu, Yiliang Zhang, Ziang Weng, Longtao Huang. Other contributors include Dongjie Zhang and Libin Dong. p. 3 For comprehensive overviews of LLMs in
cybersecurity, we refer readers to recent surveys (Xu et al. , 2025; Zhang et al.Where the paper says it
References
Rishabh Agarwal et al. On-policy distillation of language models: Learning from self-generated mistakes. p. 5 In their raw form, these artifacts manifest as domain-specific
sequences of memory addresses, hexadecimal bytes, or domain-specific language (DSL) tokens, rendering
direct representation learning highly inefficient. To overcome this, we pair each raw artifact with a concise,
synthetically generated natural-language explanation that articulates its semantics, security implications,
and operational context, effectively transforming specialized tool outputs into self-contained, semantically
rich training instances. , 2025)
introduced Group Relative Policy Optimization (GRPO) (Shao et al. , 2024), which replaces a learned
critic with intra-group relative rewards and allows deliberate reasoning behavior to emerge organically
during reinforcement learning. To accommodate heterogeneous
computational budgets, we additionally devise a knowledge distillation pipeline that transfers aligned
capabilities into compact variants (≤4B). As depicted in Figure 1, we carry out extensive evaluation on a multi-dimensional benchmark suite
comprising 35 general-purpose benchmarks across 9 categories and 15 cybersecurity-specific benchmarks
spanning threat intelligence, vulnerability analysis, security knowledge, and certification. This depth of domain comprehension—the capacity to fluidly integrate cross-layer knowledge, perform
multi-step causal inference, and translate analytical conclusions into concrete security actions—cannot
be reliably elicited through prompting or context augmentation alone; it necessitates the model having
internalized the structural and causal patterns of the domain through dedicated training. Most recently, frontier proprietary models have begun to turn their attention squarely to cybersecurity:
Anthropic’s Claude Mythos Preview (Anthropic, 2026) exhibits emergent offensive capabilities such as
zero-day discovery and autonomous exploit chain construction, while OpenAI’s GPT-5. This depth of domain comprehension—the capacity to fluidly integrate cross-layer knowledge, perform
multi-step causal inference, and translate analytical conclusions into concrete security actions—cannot
be reliably elicited through prompting or context augmentation alone; it necessitates the model having
internalized the structural and causal patterns of the domain through dedicated training. Most recently, frontier proprietary models have begun to turn their attention squarely to cybersecurity:
Anthropic’s Claude Mythos Preview (Anthropic, 2026) exhibits emergent offensive capabilities such as
zero-day discovery and autonomous exploit chain construction, while OpenAI’s GPT-5. 1-8B-Base in particular demonstrating robust
capabilities in reasoning and code generation that make it a natural initialization point for securityfocused models. Alibaba’s Qwen series (Bai et al. XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605. XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605. , 2025), and
Colibri (ColibriAI, 2025) show that task-specific supervision can yield strong performance on welldefined problems such as phishing analysis or vulnerability classification, though the relatively small
data scales involved (typically 14K–55K samples) and the absence of deep knowledge injection often
constrain generalization. More recent models have pushed further by appending reinforcement learning
stages: BaronLLM (BaronSecurity, 2025), SecurityLLM (ZySec-AI , 2024), and Foundation-Sec-8BReasoning (Yang et al. This depth of domain comprehension—the capacity to fluidly integrate cross-layer knowledge, perform
multi-step causal inference, and translate analytical conclusions into concrete security actions—cannot
be reliably elicited through prompting or context augmentation alone; it necessitates the model having
internalized the structural and causal patterns of the domain through dedicated training. Most recently, frontier proprietary models have begun to turn their attention squarely to cybersecurity:
Anthropic’s Claude Mythos Preview (Anthropic, 2026) exhibits emergent offensive capabilities such as
zero-day discovery and autonomous exploit chain construction, while OpenAI’s GPT-5. , 2025), and
Colibri (ColibriAI, 2025) show that task-specific supervision can yield strong performance on welldefined problems such as phishing analysis or vulnerability classification, though the relatively small
data scales involved (typically 14K–55K samples) and the absence of deep knowledge injection often
constrain generalization. More recent models have pushed further by appending reinforcement learning
stages: BaronLLM (BaronSecurity, 2025), SecurityLLM (ZySec-AI , 2024), and Foundation-Sec-8BReasoning (Yang et al. In their raw form, these artifacts manifest as domain-specific
sequences of memory addresses, hexadecimal bytes, or domain-specific language (DSL) tokens, rendering
direct representation learning highly inefficient. To overcome this, we pair each raw artifact with a concise,
synthetically generated natural-language explanation that articulates its semantics, security implications,
and operational context, effectively transforming specialized tool outputs into self-contained, semantically
rich training instances. May 4, 2026
XekRung Technical Report
Alibaba Security AGI Lab
Abstract
We present XekRung, a frontier large language model for cybersecurity, designed to
provide comprehensive security capabilities. To achieve this, we develop diverse
data synthesis pipelines tailored to the cybersecurity domain, enabling the scalable
construction of high-quality training data and providing a strong foundation for
cybersecurity knowledge and understanding. 21%) by over 12 percentage points on domain tasks. Crucially,
these domain gains come with minimal degradation of general capabilities: XekRung-8B retains 72. Model capabilities are
evolving beyond elementary dialogue and factual recall toward assisting humans in tackling concrete,
high-complexity real-world problems (Grattafiori et al. , 2024; Qwen Team, 2025a; DeepSeek-AI, 2024;
Jaech et al. XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605. XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605. , names, email addresses, phone numbers), anonymize internal identifiers and proprietary asset
references, and selectively truncate or remove long, semantically vacuous encoded strings (e. ,
Base64 blocks, URL tracking parameters, session tokens). XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605. XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605. , 2025), and
Colibri (ColibriAI, 2025) show that task-specific supervision can yield strong performance on welldefined problems such as phishing analysis or vulnerability classification, though the relatively small
data scales involved (typically 14K–55K samples) and the absence of deep knowledge injection often
constrain generalization. More recent models have pushed further by appending reinforcement learning
stages: BaronLLM (BaronSecurity, 2025), SecurityLLM (ZySec-AI , 2024), and Foundation-Sec-8BReasoning (Yang et al. XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605. Combined with the
progressive long-context schedule described above for agentic trajectories, repository-level samples
further consolidate the model’s ability to maintain structural understanding across long sequences, laying
the foundation for code-agent and security-audit capabilities acquired in post-training. 3 Linearized SFT Data Integration
We integrate a diverse collection of SFT datasets—spanning cybersecurity question answering, code
understanding, vulnerability analysis, and general instruction-following—by stripping chat templates
and role markers, reformulating each sample as a plain-text continuation sequence, and training it under
8 , 2024; Qwen Team, 2025a; DeepSeek-AI, 2024;
Jaech et al. As reasoning and code generation proficiencies continue to mature, identifying
application domains of sufficient difficulty has itself become a central proposition for probing and
extending the capability frontier of LLMs. Combined with the
progressive long-context schedule described above for agentic trajectories, repository-level samples
further consolidate the model’s ability to maintain structural understanding across long sequences, laying
the foundation for code-agent and security-audit capabilities acquired in post-training. 3 Linearized SFT Data Integration
We integrate a diverse collection of SFT datasets—spanning cybersecurity question answering, code
understanding, vulnerability analysis, and general instruction-following—by stripping chat templates
and role markers, reformulating each sample as a plain-text continuation sequence, and training it under
8 XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605. , 2026) each combine SFT with RL to improve alignment and reasoning reliability,
though none begins from a domain-pretrained checkpoint, leaving a gap in foundational domain coverage. 0 (Clouditera, 2025) is the closest predecessor to our own pipeline, employing CPT followed
by SFT and RL on Qwen2. We organize the data pipeline into four stages: collection, processing,
domain-specific data strategies, and data mixture. 1 Data Collection
We assemble a large-scale, multi-source cybersecurity corpus that spans five complementary categories:
• Open-source and external data. 1-8B SFT → RL
SecGPT-2. 0 (Clouditera, 2025) Qwen2. Model capabilities are
evolving beyond elementary dialogue and factual recall toward assisting humans in tackling concrete,
high-complexity real-world problems (Grattafiori et al. , 2024; Qwen Team, 2025a; DeepSeek-AI, 2024;
Jaech et al. This enables the model to internalize the endto-end reasoning chain—spanning fault discovery, root-cause localization, and patch generation—
that epitomizes expert software engineering practice. This approach aligns with recent findings in
reinforcement learning from software evolution (Wei et al. May 4, 2026
XekRung Technical Report
Alibaba Security AGI Lab
Abstract
We present XekRung, a frontier large language model for cybersecurity, designed to
provide comprehensive security capabilities. To achieve this, we develop diverse
data synthesis pipelines tailored to the cybersecurity domain, enabling the scalable
construction of high-quality training data and providing a strong foundation for
cybersecurity knowledge and understanding. Second, the associated search space is vast: adversarial behaviors can manifest across an enormous
landscape of possible configurations, inputs, and execution paths, rendering exhaustive enumeration
infeasible and demanding strategic, heuristic-guided exploration. Third, and most critically, causal
chains are often deeply concealed and counterintuitive—a security vulnerability may stem from subtle
interactions, such as a type confusion triggered under a rare compiler optimization path or a privilege
escalation enabled by an undocumented kernel behavior, that demand multi-step reasoning to identify
and resolve. XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605. XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605. XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605. XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605. May 4, 2026
XekRung Technical Report
Alibaba Security AGI Lab
Abstract
We present XekRung, a frontier large language model for cybersecurity, designed to
provide comprehensive security capabilities. To achieve this, we develop diverse
data synthesis pipelines tailored to the cybersecurity domain, enabling the scalable
construction of high-quality training data and providing a strong foundation for
cybersecurity knowledge and understanding. To accommodate heterogeneous
computational budgets, we additionally devise a knowledge distillation pipeline that transfers aligned
capabilities into compact variants (≤4B). As depicted in Figure 1, we carry out extensive evaluation on a multi-dimensional benchmark suite
comprising 35 general-purpose benchmarks across 9 categories and 15 cybersecurity-specific benchmarks
spanning threat intelligence, vulnerability analysis, security knowledge, and certification. 4 Post-Training
This section provides a comprehensive account of the post-training technical framework. The pipeline
systematically integrates rigorous data quality control, scalable synthetic data generation, and advanced
alignment methodologies, encompassing supervised fine-tuning (SFT), multi-task reinforcement learning
(RL), and adversarial self-evolution mechanisms, as well as structured knowledge distillation that
transfers the aligned capabilities of large-scale models into compact models for efficient deployment. Second, the associated search space is vast: adversarial behaviors can manifest across an enormous
landscape of possible configurations, inputs, and execution paths, rendering exhaustive enumeration
infeasible and demanding strategic, heuristic-guided exploration. Third, and most critically, causal
chains are often deeply concealed and counterintuitive—a security vulnerability may stem from subtle
interactions, such as a type confusion triggered under a rare compiler optimization path or a privilege
escalation enabled by an undocumented kernel behavior, that demand multi-step reasoning to identify
and resolve. The corpus consists of heterogeneous
cybersecurity data from multiple sources, curated through a unified pipeline of cleaning, augmentation,
and format normalization. On top of the curated corpus, we introduce code-centric signals that explicitly
encode engineering experience, thereby improving the efficiency with which tacit domain expertise is
absorbed. 1 Introduction
The development of large language models (LLMs) has entered a pivotal phase. Model capabilities are
evolving beyond elementary dialogue and factual recall toward assisting humans in tackling concrete,
high-complexity real-world problems (Grattafiori et al. Foundation-Sec8B (Kassianik et al. , 2025) conducts continued pre-training atop Llama; Primus (Yu et al. Following a breadth-first, specialization-second curriculum
principle, we therefore reserve long-horizon agentic data for injection during mid-training. Two-Dimensional Curriculum Learning. May 4, 2026
XekRung Technical Report
Alibaba Security AGI Lab
Abstract
We present XekRung, a frontier large language model for cybersecurity, designed to
provide comprehensive security capabilities. To achieve this, we develop diverse
data synthesis pipelines tailored to the cybersecurity domain, enabling the scalable
construction of high-quality training data and providing a strong foundation for
cybersecurity knowledge and understanding. , names, email addresses, phone numbers), anonymize internal identifiers and proprietary asset
references, and selectively truncate or remove long, semantically vacuous encoded strings (e. ,
Base64 blocks, URL tracking parameters, session tokens). Security tasks
frequently require not just recalling that a particular vulnerability class exists, but understanding the
precise conditions under which it manifests, reasoning about its exploitability across interacting system
components, and synthesizing actionable remediation strategies grounded in operational constraints. This depth of domain comprehension—the capacity to fluidly integrate cross-layer knowledge, perform
multi-step causal inference, and translate analytical conclusions into concrete security actions—cannot
be reliably elicited through prompting or context augmentation alone; it necessitates the model having
internalized the structural and causal patterns of the domain through dedicated training. Following a breadth-first, specialization-second curriculum
principle, we therefore reserve long-horizon agentic data for injection during mid-training. Two-Dimensional Curriculum Learning. XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605. Model capabilities are
evolving beyond elementary dialogue and factual recall toward assisting humans in tackling concrete,
high-complexity real-world problems (Grattafiori et al. , 2024; Qwen Team, 2025a; DeepSeek-AI, 2024;
Jaech et al. 1 Introduction
The development of large language models (LLMs) has entered a pivotal phase. Model capabilities are
evolving beyond elementary dialogue and factual recall toward assisting humans in tackling concrete,
high-complexity real-world problems (Grattafiori et al. XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605. XekRung achieves leading
results on all evaluated dimensions. 1
arXiv:2605. This compels the student to actively diagnose and correct its native generation
patterns, yielding robust improvements in out-of-distribution generalization. For the explicit distillation objective, we supplant traditional KL divergence with ABKD (Wang et al. In their raw form, these artifacts manifest as domain-specific
sequences of memory addresses, hexadecimal bytes, or domain-specific language (DSL) tokens, rendering
direct representation learning highly inefficient. To overcome this, we pair each raw artifact with a concise,
synthetically generated natural-language explanation that articulates its semantics, security implications,
and operational context, effectively transforming specialized tool outputs into self-contained, semantically
rich training instances. This compels the student to actively diagnose and correct its native generation
patterns, yielding robust improvements in out-of-distribution generalization. For the explicit distillation objective, we supplant traditional KL divergence with ABKD (Wang et al. Model capabilities are
evolving beyond elementary dialogue and factual recall toward assisting humans in tackling concrete,
high-complexity real-world problems (Grattafiori et al. , 2024; Qwen Team, 2025a; DeepSeek-AI, 2024;
Jaech et al.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
How the training signal is built
The authors devise a complete three-stage training pipeline spanning Continued Pre-Training (CPT), Supervised Fine-Tuning (SFT), and Multi-Task Reinforcement Learning. The pre-training stage exposes the base model to a curated cybersecurity corpus, establishing foundational understanding of security concepts, terminology, and ontology. p. 4 Our training curriculum further separates base pre-training from a dedicated mid-training
stage, in which higher-order capabilities—long-horizon agentic planning, supervised task knowledge,
and repository-level long-context code understanding—are injected without compromising the general
competence established in the base stage. 1 Data Curation and Processing
Building a cybersecurity-specialized foundation model requires a training corpus that captures both
the breadth and depth of the domain, ranging from high-level threat intelligence narratives to lowlevel binary analysis artifacts. On top of the curated corpus, we introduce code-centric signals that explicitly
encode engineering experience, thereby improving the efficiency with which tacit domain expertise is
absorbed. Our training curriculum further separates base pre-training from a dedicated mid-training
stage, in which higher-order capabilities—long-horizon agentic planning, supervised task knowledge,
and repository-level long-context code understanding—are injected without compromising the general
competence established in the base stage. Building upon this foundation, it advances to a multi-task RL phase powered by Group
Relative Policy Optimization (GRPO). Ultimately, a self-evolutionary loop grounded in verifiable code
execution ensures sustained breakthroughs in complex reasoning.Where the paper says it
Where the paper says it
Where the paper says it
Where the gains come from
The gains stem from the synergy of a well-integrated, full-pipeline training paradigm, domain-tailored data engineering, and multi-task RL. The methodology is predicated on extreme capability decomposition and compositional generalization. p. 2 XekRung undergoes a complete training pipeline
spanning Continued Pre-Training (CPT), Supervised Fine-Tuning (SFT), and Multi-Task Reinforcement
Learning, with each stage engineered around the unique data characteristics and task diversity of
the cybersecurity domain. Our methodology is predicated on extreme capability decomposition and
compositional generalization: we systematically disentangle the core task dimensions of cybersecurity—
vulnerability analysis, threat intelligence, secure code engineering, and agentic security operations—and
reassemble them through targeted training that engenders mutual reinforcement across dimensions. Our methodology is predicated on extreme capability decomposition and
compositional generalization: we systematically disentangle the core task dimensions of cybersecurity—
vulnerability analysis, threat intelligence, secure code engineering, and agentic security operations—and
reassemble them through targeted training that engenders mutual reinforcement across dimensions. To bridge the gap between surface-level knowledge and deep operational understanding (the core
limitation of general-purpose models identified above), we devise domain-aware data construction
and synthesis strategies that enrich rare yet decision-critical security concepts, model cross-artifact
dependencies, and transform opaque security artifacts into self-explanatory training instances—
collectively enabling the model to internalize the structural and causal patterns of the domain rather
than merely memorizing isolated facts. To bridge the gap between surface-level knowledge and deep operational understanding (the core
limitation of general-purpose models identified above), we devise domain-aware data construction
and synthesis strategies that enrich rare yet decision-critical security concepts, model cross-artifact
dependencies, and transform opaque security artifacts into self-explanatory training instances—
collectively enabling the model to internalize the structural and causal patterns of the domain rather
than merely memorizing isolated facts. To overcome the limitations of narrow task-specific RL (the
key deficit of existing domain models), we design a unified multi-task RL framework that integrates
Reasoning RL with verifiable rewards for analytical tasks and Agentic RL for multi-step tool-augmented
operational workflows, complemented by an adversarial self-evolution mechanism for continuous
capability escalation. Existing efforts, where RL is employed at all, tend to target isolated subtasks rather than
pursuing a unified, multi-task RL framework capable of jointly optimizing analytical reasoning, agentic
workflows, and behavioral alignment within the security domain. To address these challenges, we introduce XekRung, a cybersecurity-specialized large language model
built upon the Qwen foundation (Qwen Team, 2025a). To overcome the limitations of narrow task-specific RL (the
key deficit of existing domain models), we design a unified multi-task RL framework that integrates
Reasoning RL with verifiable rewards for analytical tasks and Agentic RL for multi-step tool-augmented
operational workflows, complemented by an adversarial self-evolution mechanism for continuous
capability escalation. The current release, XekRung, is architected as a non-thinking model that
directly emits high-fidelity responses without explicit intermediate reasoning traces, delivering stateof-the-art results with exceptional token efficiency—a decisive advantage for latency-sensitive security
operations such as real-time alert triage and interactive threat analysis.Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
Where the paper says it
In this technical report, we introduce XekRung, a frontier large language model tailored for the cybersecurity. The authors will further expand the model’s agentic capabilities and investigate the potential of self-evolution for cybersecurity. p. 2 To bridge the gap between surface-level knowledge and deep operational understanding (the core
limitation of general-purpose models identified above), we devise domain-aware data construction
and synthesis strategies that enrich rare yet decision-critical security concepts, model cross-artifact
dependencies, and transform opaque security artifacts into self-explanatory training instances—
collectively enabling the model to internalize the structural and causal patterns of the domain rather
than merely memorizing isolated facts. To overcome the limitations of narrow task-specific RL (the
key deficit of existing domain models), we design a unified multi-task RL framework that integrates
Reasoning RL with verifiable rewards for analytical tasks and Agentic RL for multi-step tool-augmented
operational workflows, complemented by an adversarial self-evolution mechanism for continuous
capability escalation.Where the paper says it
Green — the paper says it, and the page is printed. Red — no passage carries it, so treat that sentence as unverified. The same check runs on your own text: check a summary against its source, $5.
Improvements for AI systems
- Data Synthesis Pipelines for Cybersecurity Knowledge
Improve AI systems by developing diverse data synthesis pipelines tailored to cybersecurity, enabling high-quality training data construction through contextual enrichment
and targeted synthesis pipelines on the construction side.
This allows models to internalize the structural and causal patterns of the domain rather than merely memorizing isolated facts.
- Complete Training Pipeline for Domain Specialization
Implement a full CPT to SFT to RL pipeline with task-aware specialization, specifically using Group Relative Policy Optimization (GRPO)
for multi-task reinforcement learning. This allows the model to achieve deep domain expertise while maintaining broad general-purpose competence
by optimizing Reasoning RL with Verifiable Rewards (RLVR).
- Enhanced Reasoning and Tool Orchestration
The system can perform complex, multi-step security analysis tasks such as automated penetration testing, large-scale vulnerability detection and validation, red-team long-chain attack simulation, and multi-stage incident response.
This is achieved through Agentic RL for end-to-end workflow optimization
complemented by ActionRL
to focus supervision on the Branch Divergence Point.
- Cross-Scale Competitiveness in Deployment
The improved AI can achieve state of the art performance on cybersecurity benchmarks while maintaining strong general performance, demonstrating that a model can match or exceed models with several times more parameters on domain-specific tasks, while offering substantially faster inference—a critical advantage for latency-sensitive security operations.
- Robust Vulnerability Root Cause Mapping
The model can perform specific analytical tasks like Root Cause Mapping (RCM): Predicting CWE identifiers from CVE semantics, evaluated via a strict binary exact-match indicator
and Vulnerability Severity Prediction (VSP): Forecasting aggregate CVSS scores alongside granular metric components.
Abstract
We present XekRung, a frontier large language model for cybersecurity, designed to provide comprehensive security capabilities. To achieve this, we develop diverse data synthesis pipelines tailored to the cybersecurity domain, enabling the scalable construction of high-quality training data and providing a strong foundation for cybersecurity knowledge and understanding. Building on this foundation, we establish a complete training pipeline spanning continued pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL) to further extend the model's capabilities. We further introduce a multi-dimensional evaluation system to guide the iterative improvement of both domain-specific and general-purpose abilities. Extensive experiments demonstrate that XekRung achieves state-of-the-art performance on cybersecurity-specific benchmarks among models of the same scale, while maintaining strong performance on general benchmarks.
Sources
- Qwen Technical Report
- Does your data spark joy? Performance gains from domain upsampling at the end of training
- Gradient Similarity Surgery in Multi-Task Deep Learning
- AlpaGasus: Training A Better Alpaca with Fewer Data
- Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge
- Training Verifiers to Solve Math Word Problems
- Spatially Resolved Observations of Betelgeuse at 7mm and 1.3cm Just Prior to the Great Dimming
- DeepSeek-V3 Technical Report
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- CLewR: Curriculum Learning with Restarts for Machine Translation Preference Learning
- Flow-Induced Vibration of Flexible Hydrofoil Within Cavitating Turbulent Flow
- The Llama 3 Herd of Models
- A C++20 Interface for MPI 4.0
- OpenAI o1 System Card
- EntropyLong: Effective Long-Context Training via Predictive Uncertainty
- Llama-3.1-FoundationAI-SecurityLLM-Base-8B Technical Report
- Estimating rank-one matrices with mismatched prior and noise: universality and large deviations
- How to Correctly do Semantic Backpropagation on Language-based Agentic Systems
- MSSR: Memory-Aware Adaptive Replay for Continual LLM Fine-Tuning
- Qwen3 Technical Report
Related papers
- From Strategy Search to Policy Learning: MCTS-Guided Adversarial Co-Evolution for LLM Safety Alignment
- Privacy Leakage from Recurrent State in LLM Inference
- Incrementally Verifiable Oracle Aided Computation
- Privilege and confidentiality in generative AI workflows
- BadMoE: Backdooring Mixture-of-Experts LLMs via Routing-Aware Triggers and Task-Underutilized Experts
- CoVault: Secure, Scalable Analytics of Personal Data