mlsanityData to 14 Oct 2026

PaSa: An LLM Agent for Comprehensive Academic Paper Search

arXiv 2501.10120 ↗First posted 17 Jan 2025cs.IR cs.LGcited by 64

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

We introduce PaSa, an advanced Paper Search agent powered by large language models. PaSa can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant references, to ultimately obtain comprehensive and accurate results for complex scholar queries. We optimize PaSa using reinforcement learning with a synthetic dataset, AutoScholarQuery, which includes 35k fine-grained academic queries and corresponding papers sourced from top-tier AI conference publications. Additionally, we develop RealScholarQuery, a benchmark collecting real-world academic queries to assess PaSa performance in more realistic scenarios. Despite being trained on synthetic data, PaSa significantly outperforms existing baselines on RealScholarQuery, including Google, Google Scholar, Google with GPT-4o for paraphrased queries, ChatGPT (search-enabled GPT-4o), GPT-o1, and PaSa-GPT-4o (PaSa implemented by prompting GPT-4o). Notably, PaSa-7B surpasses the best Google-based baseline, Google with GPT-4o, by 37.78% in recall@20 and 39.90% in recall@50, and exceeds PaSa-GPT-4o by 30.36% in recall and 4.25% in precision. Model, datasets, and code are available at https://github.com/bytedance/pasa.

Key facts. Cited by 64 papers in the map (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 16 of its 36 references that are in the map. First posted on arXiv 17 Jan 2025.

Builds on

16 of 36 references.

Closest ancestors · 1

Same direction, newest first

  1. 2023Mind2Web: Towards a Generalist Agent for the Web9 Jun

Other references · 15

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  3. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  4. 2023ChemCrow: Augmenting large-language models with chemistry toolscited by 631
  5. 2022A Systematic Evaluation of Large Language Models of Codecited by 363
  6. 2023AutoAgents: A Framework for Automatic Agent Generationcited by 216
  7. 2024Agent Q: Advanced Reasoning and Learning for Autonomous AI Agentscited by 208
  8. 2023SciMON: Scientific Inspiration Machines Optimized for Noveltycited by 179
  9. 2024Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Modelscited by 154
  10. 2024LitLLM: A Toolkit for Scientific Literature Reviewcited by 63
  11. 2023Large Language Model based Long-tail Query Rewriting in Taobao Searchcited by 62
  12. 2024LLMs as Research Tools: A Large Scale Survey of Researchers' Usage and Perceptionscited by 47
3 more
  1. 2023Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiencycited by 46
  2. 2024AGILE: A Novel Reinforcement Learning Framework of LLM Agentscited by 45
  3. 2024Robust Planning with LLM-Modulo Framework: Case Study in Travel Planningcited by 34

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 31; 2026: 33.

64 papers.

Sort:

By area:

  1. 2025Towards Scientific Intelligence: A Survey of LLM-based Scientific Agentscited by 98
  2. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 62
  3. 2025A Survey of LLM-Driven AI Agent Communication: Protocols, Security Risks, and Defense Countermeasurescited by 57
  4. 2025Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agentscited by 46
  5. 2025Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluationcited by 42
  6. 2025A Survey of Large Language Model Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrievalcited by 33
  7. 2025When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Researchcited by 26
  8. 2025AI Scientists Fail Without Strong Implementation Capabilitycited by 21
  9. 2025DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seekingcited by 21
  10. 2025Enterprise Deep Research: Steerable Multi-Agent Deep Research for Enterprise Analyticscited by 20
  11. 2026WebGym: Scaling Training Environments for Visual Web Agents with Realistic Taskscited by 19
  12. 2025InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generationcited by 15
38 more
  1. 2025Reinforcement Learning Foundations for Deep Research Systems: A Surveycited by 14
  2. 2026AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discoverycited by 11
  3. 2026AI for Auto-Research: Roadmap & User Guidecited by 11
  4. 2025LLLMs: A Data-Driven Survey of Evolving Research on Limitations of Large Language Modelscited by 9
  5. 2025Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluatorcited by 9
  6. 2026Paper2Rebuttal: A Multi-Agent Framework for Transparent Author Response Assistancecited by 9
  7. 2026CAPO: Critic-Guided Action-Aligned Policy Optimization for Advancing LLM Agent Capabilitiescited by 8
  8. 2025SPAR: Scholar Paper Retrieval with LLM-based Agents for Enhanced Academic Searchcited by 7
  9. 2026PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimizationcited by 5
  10. 2026Table-as-Search: Formulate Long-Horizon Agentic Information Seeking as Table Completioncited by 5
  11. 2025Agentic AutoSurvey: Let LLMs Survey LLMscited by 4
  12. 2025LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrievalcited by 4
  13. 2025BioMedSearch: A Multi-Source Biomedical Retrieval Framework Based on LLMscited by 4
  14. 2025Idea2Plan: Exploring AI-Powered Research Planningcited by 4
  15. 2025WisPaper: Your AI Scholar Search Enginecited by 4
  16. 2026Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Usecited by 4
  17. 2025M-DocSum: Do LVLMs Genuinely Comprehend Interleaved Image-Text in Document Summarization?cited by 3
  18. 2025OpenLens AI: Fully Autonomous Research Agent for Health Infomaticscited by 3
  19. 2025PaperAsk: A Benchmark for Reliability Evaluation of LLMs in Paper Search and Readingcited by 3
  20. 2025SciNet: Evaluating AI Agents in Relation-Aware Scientific Literature Retrievalcited by 3
  21. 2026ScholarGym: Benchmarking Large Language Model Capabilities in the Information-Gathering Stage of Deep Researchcited by 3
  22. 2026PaperGym: Rubric-Centered Evolution for Research-Plan Generationcited by 3
  23. 2025LLM×MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resourcescited by 2
  24. 2026DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answeringcited by 2
  25. 2026DeepXiv-SDK: An Agentic Data Interface for Scientific Literaturecited by 2
  26. 2026Learning to Search: A Decision-Based Agent for Knowledge-Based Visual Question Answeringcited by 2
  27. 2026Towards Recursive Self-Evolving Agentic Literature Retrievalcited by 2
  28. 2026Multi-Turn Agentic Scientific Literature Search via Workflow Inductioncited by 2
  29. 2025Agent-Centric Personalized Multiple Clustering with Multi-Modal LLMscited by 1
  30. 2025Implementing Long Text Style Transfer with LLMs through Dual-Layered Sentence and Paragraph Structure Extraction and Mappingcited by 1
  31. 2025PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexingcited by 1
  32. 2025AirQA: A Comprehensive QA Dataset for AI Research with Instance-Level Evaluationcited by 1
  33. 2025REVISION:Reflective Intent Mining and Online Reasoning Auxiliary for E-commerce Visual Search System Optimizationcited by 1
  34. 2025ADOPT: Adaptive Dependency-Guided Joint Prompt Optimization for Multi-Step LLM Pipelinescited by 1
  35. 2026ProtRLSearch: A Multi-Round Multimodal Protein Search Agent with Large Language Models Trained via Reinforcement Learningcited by 1
  36. 2026When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Searchcited by 1
  37. 2026Prompt-to-Paper: Agentic AI System for Bioinformaticscited by 1
  38. 2026Can LLM design high-quality experiments? A Comprehensive and Systematic Benchmark on Autonomous Experimental Designcited by 1

50 most cited of 64 All 64 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR
  2. 2025Beyond the limitation of a single query: Train your LLM for query expansion with Reinforcement Learning
  3. 2026SearchArt: Training Long-Horizon Search Agent with Scalable Synthetic and Verified Task
  4. 2026SmartSearch: Process Reward-Guided Query Refinement for Search Agents
  5. 2025Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty
  6. 2025AI-SearchPlanner: Modular Agentic Search via Pareto-Optimal Multi-Objective Reinforcement Learning
  7. 2023PaperQA: Retrieval-Augmented Generative Agent for Scientific Research
  8. 2026Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?