让大模型推理更可信，通过冲突检测与结构化事实双重保障。
Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Facts
- 用冲突识别代替全链验证，只聚焦分歧点提升效率
- 在GAIA上达84.4%准确率，中文题库93.8%表现优异
- 适合需要高可靠推理的复杂任务系统开发
基于大模型的长程推理常因中间步骤缺乏验证而失败。Co-Sight提出两种互补机制：冲突感知元验证（CAMV）将验证转为冲突识别与针对性证伪，仅对专家代理间的分歧热点分配计算资源，使验证成本与不一致数量挂钩，提升效率与可靠性；可信结构化事实推理（TRSF）通过结构化事实模块持续组织、验证与同步跨代理证据，确保所有推理基于已验证、可追溯的信息，并支持全程透明验证。两者形成闭环：TRSF提供结构化事实，CAMV选择性证伪或强化，实现透明可信推理。实证显示，Co-Sight在GAIA上取得84.4%的准确率，在Humanity's Last Exam上达35.5%，中文-SimpleQA上达93.8%。消融实验确认结构化事实与冲突感知验证的协同效应。该方法为大模型长程推理提供了可扩展的可靠范式。代码已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。