CHAL：面向可废止领域的多智能体辩论信念优化框架
Multi-Agent Debate for Belief Optimization in Defeasible Domains
AI 导读
论文提出 CHAL（Council of Hierarchical Agentic Language），一个将可废止论辩作为信念优化引擎的多智能体辩证框架。每个智能体维护图结构的 CHAL Belief Schema（CBS），以贝叶斯式架构和梯度驱动的动态机制实现信念修正，并把认识论、逻辑与伦理等元认知价值体系设为可配置超参数。
正文 · 原文
Abstract:Multi-agent debate has emerged as a promising approach for improving LLM reasoning on ground-truth tasks, yet current methodologies face certain structural limitations: debate tends to induce a martingale over belief trajectories, majority voting accounts for most observed gains, and LLMs exhibit confidence escalation rather than calibration across rounds. We argue that the genuine value of debate, and dialectic systems as a whole, lies not in ground-truth tasks but in defeasible domains, where every position can in principle be defeated by better reasoning. We present the Council of Hierarchical Agentic Language (CHAL), a multi-agent dialectic framework that treats defeasible argumentation as an engine for belief optimization. Each agent maintains a CHAL Belief Schema (CBS), a graph-structured belief representation with a Bayesian-inspired architecture, that facilitates belief revision through a gradient-informed dynamic mechanism by leveraging the strength of the belief's thesis as a differentiable objective. Meta-cognitive value systems spanning epistemology, logic, and ethics are elevated to configurable hyperparameters governing agent reasoning and adjudication outcomes. We provide a series of ablation experiments that demonstrate systematic and interpretable effects: the adjudicator's value system determines the debate's overall trajectories in latent belief space, council diversity refines beliefs for all participants, and the framework generalizes across broad fields. CHAL is, to our knowledge, the first framework to treat multi-agent debate as structured belief optimization over defeasible domains. Further, the auditable belief artifacts it produces establish the foundation for dedicated evaluation suites for defeasible argumentation, with broader implications for building AI systems whose reasoning and value commitments are transparent, aligned, and subject to human oversight.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2605.12718 [cs.AI] |
| (or arXiv:2605.12718v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.12718 arXiv-issued DOI via DataCite |
Submission history
From: Griffin Kent [view email]
[v1]
Tue, 12 May 2026 20:26:41 UTC (1,663 KB)
[v2]
Sun, 25 Oct 2026 22:42:37 UTC (1,627 KB)
来源：arXiv cs.AI · arxiv.org