LongCat-DeepResearch Technical Report
cs.AI
Submitted: 2026-09-28
Updated: 2026-09-28
Comments: 23 pages, 5 figures
Code: https://github.com/huggingface/smolagents
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report Revision
- MindSearch: Mimicking Human Minds Elicits Deep AI Searcher
- Don't Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination
- DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents
- Step-DeepResearch Technical Report
- Planner-Centric Reinforcement Learning for Deep Research with Structure-Aware Reward
- SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
- RhinoInsight: Improving Deep Research through Control Mechanisms for Model Behavior and Context
- AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Research
- Lost in the Middle: How Language Models Use Long Contexts
- AREX: Towards a Recursively Self-Improving Agent for Deep Research
- Self-Refine: Iterative Refinement with Self-Feedback
- WebGPT: Browser-assisted question-answering with human feedback
- MemGPT: Towards LLMs as Operating Systems
- FoldAct: Efficient and Stable Context Folding for Long-Horizon Search Agents
- ResearchRubrics: A Benchmark of Prompts and Rubrics For Evaluating Deep Research Agents
- A Tale of Two Graphs: Separating Knowledge Exploration from Outline Structure for Open-Ended Deep Research
- Language agents achieve superhuman synthesis of scientific knowledge
- CogGen: A Cognitively Inspired Recursive Framework for Deep Research Report Generation
- DeepTRACE: Auditing Deep Research AI Systems for Tracking Reliability Across Citations and Evidence
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems