Co-Sight：通过冲突感知元验证与结构化事实可信推理增强基于LLM的智能体
Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Facts
AI总结：
Co-Sight通过冲突感知元验证与结构化事实可信推理，将推理转化为可证伪可审计过程，在GAIA等基准上取得最先进准确率，实现可靠长时程推理。
摘要：
基于LLM的智能体在长时程推理中常常失败，其原因并非生成能力不足，而是对中间推理过程的验证不充分。Co-Sight通过两种互补机制将推理转变为可证伪且可审计的过程，从而解决这一挑战：冲突感知元验证（CAMV）和结构化事实可信推理（TRSF）。CAMV将验证重新表述为冲突识别和针对性证伪，仅将计算分配给专家智能体之间的分歧热点，而非整个推理链。这将验证成本限制为不一致的数量，并提高了效率和可靠性。TRSF通过结构化事实模块持续组织、验证和同步各智能体间的证据。通过维护经过验证、可追溯和可审计的知识，它确保所有推理都基于一致且来源验证的信息，并在整个推理过程中支持透明的验证。TRSF和CAMV共同形成一个闭环验证回路，其中TRSF提供结构化事实，CAMV选择性地证伪或强化这些事实，从而产生透明且可信的推理。实验上，Co-Sight在GAIA（84.4%）和Humanity's Last Exam（35.5%）上达到了最先进的准确率，并在Chinese-SimpleQA（93.8%）上取得了强劲结果。消融研究证实，结构化事实基础与冲突感知验证之间的协同作用推动了这些改进。因此，Co-Sight为基于LLM的智能体中的可靠长时程推理提供了一种可扩展的范式。代码可在https://github.com/ZTE-AICloud/Co-Sight/tree/cosight2.0_benchmarks获取。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
