mlsanityData to 14 Oct 2026

WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agents

arXiv 2509.13309 ↗First posted 16 Sep 2025cs.CLcited by 68

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Recent advances in deep-research systems have demonstrated the potential for AI agents to autonomously discover and synthesize knowledge from external sources. In this paper, we introduce WebResearcher, a novel framework for building such agents through two key components: (1) WebResearcher, an iterative deep-research paradigm that reformulates deep research as a Markov Decision Process, where agents periodically consolidate findings into evolving reports while maintaining focused workspaces, overcoming the context suffocation and noise contamination that plague existing mono-contextual approaches; and (2) WebFrontier, a scalable data synthesis engine that generates high-quality training data through tool-augmented complexity escalation, enabling systematic creation of research tasks that bridge the gap between passive knowledge recall and active knowledge construction. Notably, we find that the training data from our paradigm significantly enhances tool-use capabilities even for traditional mono-contextual methods. Furthermore, our paradigm naturally scales through parallel thinking, enabling concurrent multi-agent exploration for more comprehensive conclusions. Extensive experiments across 6 challenging benchmarks demonstrate that WebResearcher achieves state-of-the-art performance, even surpassing frontier proprietary systems.

Key facts. Cited by 68 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 21 of its 35 references that are in the map. First posted on arXiv 16 Sep 2025.

Builds on

21 of 35 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capability30 Apr
  2. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning12 Mar
  3. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  4. 2024Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation19 Sep

Other references · 17

  1. 2025Qwen3 Technical Reportcited by 8,820
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2025Gemma 3 Technical Reportcited by 1,824
  5. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  6. 2025Group Sequence Policy Optimizationcited by 835
  7. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 647
  8. 2025Humanity's Last Examcited by 491
  9. 2025GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Modelscited by 467
  10. 2025WebSailor: Navigating Super-human Reasoning for Web Agentcited by 229
  11. 2025WebDancer: Towards Autonomous Information Seeking Agencycited by 188
  12. 2025BrowseComp-ZH: Benchmarking Web Browsing Ability of Large Language Models in Chinesecited by 145
5 more
  1. 2024Leave No Document Behind: Benchmarking Long-Context LLMs with Extended Multi-Doc QAcited by 122
  2. 2025WebShaper: Agentically Data Synthesizing via Information-Seeking Formalizationcited by 121
  3. 2025WebExplorer: Explore and Evolve for Training Long-Horizon Web Agentscited by 92
  4. 2023Calibrating LLM-Based Evaluatorcited by 53
  5. 2025C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generationcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 25; 2026: 43.

68 papers.

Sort:

By area:

  1. 2025Scaling Long-Horizon LLM Agent via Context-Foldingcited by 148
  2. 2025AgentFold: Long-Horizon Web Agents with Proactive Context Managementcited by 103
  3. 2025Tongyi DeepResearch Technical Reportcited by 66
  4. 2025Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Managementcited by 51
  5. 2026REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agentscited by 49
  6. 2025Budget-Aware Tool Use Enables Effective Agent Scalingcited by 44
  7. 2025Agentic Entropy-Balanced Policy Optimizationcited by 40
  8. 2025CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agentscited by 33
  9. 2026InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discoverycited by 27
  10. 2025IterResearch: Rethinking Long-Horizon Agents with Interaction Scalingcited by 23
  11. 2025A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applicationscited by 22
  12. 2026BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?cited by 22
38 more
  1. 2025Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analyticscited by 20
  2. 2025ReForm: Reflective Autoformalization with Prospective Bounded Sequence Optimizationcited by 20
  3. 2026Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Taskscited by 18
  4. 2025Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learningcited by 17
  5. 2026Reasoning and Tool-use Compete in Agentic RL:From Quantifying Interference to Disentangled Tuningcited by 17
  6. 2025AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesiscited by 14
  7. 2025Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Factscited by 13
  8. 2026DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Usecited by 13
  9. 2025MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark for Reasoning-Intensive Multimodal Retrievalcited by 12
  10. 2025Lost in the Maze: Overcoming Context Limitations in Long-Horizon Agentic Searchcited by 12
  11. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
  12. 2026RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewardscited by 12
  13. 2025FlowSearch: Advancing deep research with dynamic structured knowledge flowcited by 10
  14. 2025WebAggregator: Enhancing Compositional Reasoning Capabilities of Deep Research Agent Foundation Modelscited by 10
  15. 2026Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalizationcited by 9
  16. 2025Beyond Pipelines: A Survey of the Paradigm Shift toward Model-Native Agentic AIcited by 8
  17. 2025EcomBench: Towards Holistic Evaluation of Foundation Agents in E-commercecited by 8
  18. 2025Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Followingcited by 8
  19. 2026WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoningcited by 8
  20. 2026Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrievalcited by 8
  21. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  22. 2026Evolving from Tool User to Creator via Training-Free Experience Reuse in Multimodal Reasoningcited by 7
  23. 2026FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agentscited by 7
  24. 2025MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoningcited by 6
  25. 2026EvoIdeator: Evolving Scientific Ideas through Checklist-Grounded Reinforcement Learningcited by 6
  26. 2026Argus: Evidence Assembly for Scalable Deep Research Agentscited by 6
  27. 2026Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report Revisioncited by 4
  28. 2026AgentCollab: A Self-Evaluation-Driven Collaboration Paradigm for Efficient LLM Agentscited by 4
  29. 2026OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agentscited by 4
  30. 2026Yunque DeepResearch Technical Reportcited by 3
  31. 2026ProductResearch: Training E-Commerce Deep Research Agents via Multi-Agent Synthetic Trajectory Distillationcited by 3
  32. 2026AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoningcited by 3
  33. 2026Effective Reinforcement Learning for Agentic Search by Recycling Zero-Variance Queries During Trainingcited by 3
  34. 2026ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RLcited by 3
  35. 2025MARS: Co-evolving Dual-System Deep Research via Multi-Agent Reinforcement Learningcited by 2
  36. 2026Dynamic Mixed-Precision Routing for Efficient Multi-step LLM Interactioncited by 2
  37. 2026CoPE: Clipped RoPE as A Scalable Free Lunch for Long Context LLMscited by 2
  38. 2026Orchestra-o1: Omnimodal Agent Orchestrationcited by 2

50 most cited of 68 All 68 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning
  2. 2025Deep Research Bench: Evaluating AI Web Research Agents
  3. 2025Deep Research: A Survey of Autonomous Research Agents
  4. 2025DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments
  5. 2026EigentSearch-Q+: Enhancing Deep Research Agents with Structured Reasoning Tools
  6. 2025Deep Research Agents: A Systematic Examination And Roadmap
  7. 2025From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents
  8. 2025DatasetResearch: Benchmarking Agent Systems for Demand-Driven Dataset Discovery