FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents

arXiv:2606.12087 · cs.CL · Submitted 2026-06-10 · Read on arXiv

cs.CL

Submitted: 2026-06-10

Updated: 2026-10-12

Code: https://github.com/RUCAIBox/FORT-Searcher

Terminology

• Benchmark — 1× in this paper · explained in 2 episodes
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Graph Construction — 1× in this paper · explained in 3 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes

Sources

• NanoFlux: Adversarial Dual-LLM Evaluation and Distillation For Multi-Domain Reasoning
• xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations
• REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents
• OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
• OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data
• AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning
• SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent
• Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
• VAULT: Vigilant Adversarial Updates via LLM-Driven Retrieval-Augmented Generation for NLI
• DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
• DeepDive: Advancing Deep Search Agents with Knowledge Graphs and Multi-Turn RL
• SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models
• WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents
• HopWeaver: Cross-Document Synthesis of High-Quality and Authentic Multi-Hop Questions
• OpenAI GPT-5 System Card
• R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning
• WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization
• Kimi K2.5: Visual Agentic Intelligence
• LongCat-Flash-Thinking-2601 Technical Report
• MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering