CHAL: Council of Hierarchical Agentic Language

arXiv cs.AI Papers
multi-agent llm-reasoning debate belief-optimization defeasible-argumentation framework

Summary

This paper introduces CHAL, a multi-agent dialectic framework that treats defeasible argumentation as structured belief optimization for LLM reasoning, using configurable meta-cognitive value systems and a gradient-informed belief revision mechanism.

arXiv:2605.12718v1 Announce Type: new 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.
Original Article
View Cached Full Text

Cached at: 05/14/26, 06:14 AM 

# CHAL: Council of Hierarchical Agentic Language
Source: [https://arxiv.org/abs/2605.12718](https://arxiv.org/abs/2605.12718)
[View PDF](https://arxiv.org/pdf/2605.12718)

> 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\.

## Submission history

From: Griffin Kent \[[view email](https://arxiv.org/show-email/6a1ef802/2605.12718)\] **\[v1\]**Tue, 12 May 2026 20:26:41 UTC \(1,663 KB\)

Similar Articles

Adaptive Latent Agentic Reasoning

arXiv cs.CL

This paper introduces Adaptive Latent Agentic Reasoning (ALAR), a dual-mode framework for LLM agents that uses compact latent reasoning for routine turns and selectively escalates to explicit chain-of-thought for harder decisions, achieving up to 84.6% token reduction while maintaining task accuracy.

Hidden Anchors in Multi-Agent LLM Deliberation

arXiv cs.AI

This paper models multi-agent LLM deliberation as a closed-loop dynamical system where each agent has a hidden internal belief (anchor) that continually pulls its opinion, and shows how this anchor can be recovered from deliberation data alone, explaining phenomena like opinions escaping the convex hull of initial beliefs.