Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Hongwei, Lu, Ji, Jiang, Shiqing, Zhu, Chenxiang, Xie, Li, Zhong, Chen, Chen, Haoran, Zhu, Yurui, Du, Yongsheng, Gao, Yanqin, Huang, Lingjun, Wang, Baoli, Tan, Fang, Zou, Peng
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2510.21557
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915574571859968
author Zhang, Hongwei
Lu, Ji
Jiang, Shiqing
Zhu, Chenxiang
Xie, Li
Zhong, Chen
Chen, Haoran
Zhu, Yurui
Du, Yongsheng
Gao, Yanqin
Huang, Lingjun
Wang, Baoli
Tan, Fang
Zou, Peng
author_facet Zhang, Hongwei
Lu, Ji
Jiang, Shiqing
Zhu, Chenxiang
Xie, Li
Zhong, Chen
Chen, Haoran
Zhu, Yurui
Du, Yongsheng
Gao, Yanqin
Huang, Lingjun
Wang, Baoli
Tan, Fang
Zou, Peng
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_21557
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Facts
Zhang, Hongwei
Lu, Ji
Jiang, Shiqing
Zhu, Chenxiang
Xie, Li
Zhong, Chen
Chen, Haoran
Zhu, Yurui
Du, Yongsheng
Gao, Yanqin
Huang, Lingjun
Wang, Baoli
Tan, Fang
Zou, Peng
Artificial Intelligence
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.
title Co-Sight: Enhancing LLM-Based Agents via Conflict-Aware Meta-Verification and Trustworthy Reasoning with Structured Facts
topic Artificial Intelligence
url https://arxiv.org/abs/2510.21557