mlsanityData to 7 Oct 2026

Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Facts

arXiv 2510.21557 ↗First posted 24 Oct 2025cs.AIcited by 12

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

Long-horizon reasoning in LLM-based agents often fails not from generative weakness but from insufficient verification of intermediate reasoning. Co-Sight addresses this challenge by turning reasoning into a falsifiable and auditable process through two complementary mechanisms: Conflict-Aware Meta-Verification (CAMV) and Trustworthy Reasoning with Structured Facts (TRSF). CAMV reformulates verification as conflict identification and targeted falsification, allocating computation only to disagreement hotspots among expert agents rather than to full reasoning chains. This bounds verification cost to the number of inconsistencies and improves efficiency and reliability. TRSF continuously organizes, validates, and synchronizes evidence across agents through a structured facts module. By maintaining verified, traceable, and auditable knowledge, it ensures that all reasoning is grounded in consistent, source-verified information and supports transparent verification throughout the reasoning process. Together, TRSF and CAMV form a closed verification loop, where TRSF supplies structured facts and CAMV selectively falsifies or reinforces them, yielding transparent and trustworthy reasoning. Empirically, Co-Sight achieves state-of-the-art accuracy on GAIA (84.4%) and Humanity's Last Exam (35.5%), and strong results on Chinese-SimpleQA (93.8%). Ablation studies confirm that the synergy between structured factual grounding and conflict-aware verification drives these improvements. Co-Sight thus offers a scalable paradigm for reliable long-horizon reasoning in LLM-based agents. Code is available at https://github.com/ZTE-AICloud/Co-Sight/tree/cosight2.0_benchmarks.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 35 of its 37 references that are in the map. First posted on arXiv 24 Oct 2025.

Builds on

35 of 37 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025WebSailor: Navigating Super-human Reasoning for Web Agent3 Jul
  2. 2025Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents31 May
  3. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review28 Apr
  4. 2024Diversity of Thought Elicits Stronger Reasoning Capabilities in Multi-Agent Debate Frameworks10 Oct

Other references · 31

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  6. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  7. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  8. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  9. 2023Graph of Thoughts: Solving Elaborate Problems with Large Language Modelscited by 873
  10. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  11. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  12. 2024A Survey on the Memory Mechanism of Large Language Model based Agentscited by 622
19 more
  1. 2025Why Do Multi-Agent LLM Systems Fail?cited by 559
  2. 2025Humanity's Last Examcited by 467
  3. 2024MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documentscited by 251
  4. 2023Automatically Correcting Large Language Models: Surveying the landscape of diverse self-correction strategiescited by 236
  5. 2024When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMscited by 230
  6. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  7. 2025Plan-and-Act: Improving Planning of Agents for Long-Horizon Taskscited by 190
  8. 2025Deep Research Agents: A Systematic Examination And Roadmapcited by 122
  9. 2024LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMscited by 104
  10. 2025WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agentscited by 66
  11. 2023Self-Verification Improves Few-Shot Clinical Information Extractioncited by 52
  12. 2024Internal Consistency and Self-Feedback in Large Language Models: A Surveycited by 49
  13. 2024Chinese SimpleQA: A Chinese Factuality Evaluation for Large Language Modelscited by 39
  14. 2025ReflAct: World-Grounded Decision Making in LLM Agents via Goal-State Reflectioncited by 30
  15. 2025AWorld: Orchestrating the Training Recipe for Agentic AIcited by 16
  16. 2024CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Taskscited by 10
  17. 2025ALAS: A Stateful Multi-LLM Agent Framework for Disruption-Aware Planningcited by 5
  18. 2025SelfCheck-Eval: A Multi-Module Framework for Zero-Resource Hallucination Detection in Large Language Modelscited by 4
  19. 2025Plan Verification for LLM-Based Embodied Task Completion Agentscited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 11.

12 papers.

  1. 2026AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applicationscited by 46
  2. 2026Autogenesis: A Self-Evolving Agent Protocolcited by 12
  3. 2026Yunjue Agent Tech Report: A Fully Reproducible, Zero-Start In-Situ Self-Evolving Agent System for Open-Ended Taskscited by 4
  4. 2025MARINE: Theoretical Optimization and Design for Multi-Agent Recursive IN-context Enhancementcited by 3
  5. 2026Learning Agent Routing From Early Experiencecited by 3
  6. 2026ScholarPeer: A Context-Aware Multi-Agent Framework for Automated Peer Reviewcited by 2
  7. 2026Lemon Agent Technical Reportcited by 1
  8. 2026TodoEvolve: Learning to Architect Agent Planning Systemscited by 1
  9. 2026ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Emergent Adaptationcited by 1
  10. 2026Avoiding Overthinking and Underthinking: Curriculum-Aware Budget Scheduling for LLMscited by 0
  11. 2026ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scalingcited by 0
  12. 2026PoTRE: Test-Time Reasoning inspired by Cognitive Heterogeneitycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing
  2. 2025COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context
  3. 2026KC-Bench: A Dynamic Interactive Benchmark for Evaluating Knowledge Conflicts in LLM Agents
  4. 2026VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks
  5. 2025Collaborative Belief Reasoning with LLMs for Efficient Multi-Agent Collaboration
  6. 2026MAVEN: Multi-Agent Verification-Elaboration Network with In-Step Epistemic Auditing
  7. 2025Recursive Knowledge Synthesis for Multi-LLM Systems: Stability Analysis and Tri-Agent Audit Framework
  8. 2026How Well Do LLMs Reason with Noisy Evidence? An Active Visual Reasoning Benchmark