arXiv AI August 20, 2026 By Xiang Yin, Adam Dejl, Antonio Rago, Lihu Chen, Francesca Toni

A Theory of Post-hoc Debate Judgement

The paper proposes a theory for judging post-hoc debates in AI, focusing on properties like reproducibility, robustness, groundedness, and explainability. It evaluates two debate‑judgement methods—LLM judges and formal computational argumentation semantics—finding similar accuracy but noting that argumentation semantics offers stronger formal guarantees. The study suggests that argumentation semantics is a preferable framework for principled debate judges in AI systems.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Jul 23

Avoiding Obfuscation with Prover-Estimator Debate

arXiv:2506. 13609v2 Announce Type: replace Abstract: Training powerful AI systems to exhibit desired behaviors hinges on the ability to provide accurate human supervision on increasingly complex tasks.

By Jonah Brown-Cohen, Geoffrey Irving, Georgios Piliouras, Lijie Chen, Jiawei Li, Zhiyang Xun

arXiv AI

Jul 31

Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges

arXiv:2607. 26212v1 Announce Type: cross Abstract: Multi-Agent Debate (MAD) is a promising paradigm for improving the accuracy and robustness of Large Language Model (LLM)-based agentic systems.

By Quim Motger, Marc Oriol, Jordi Marco, Xavier Franch

llms agents benchmarks

arXiv Computation and Language

2d ago

Evaluating the Capabilities of LLMs for Persuasive Dialogue

The paper introduces “Persuasio”, a multi‑agent dialogue platform that uses a formal argumentation theory to adjudicate winners in free‑text debates. Using this system, the authors generated 192 debates on a UK political topic involving humans and large language models (LLMs), and evaluated 22 interlocutors through automated adjudication and 9,702 crowdsourced pairwise judgments across 1,386 annotation instances. The results show a consistent decoupling between subjective persuasiveness—where LLMs dominate—and formal argumentative strength—where humans remain competitive, with multi‑agent and retrieval‑augmented variants widening this gap.

By Jordan Robinson, Angus R. Williams, Katie Atkinson, Anthony G. Cohn

llms rag agents

arXiv AI

Jun 10

The Confident Liar: Diagnosing Multi-Agent Debate with Log-Probabilities and LLM-as-Judge

arXiv:2606. 10296v1 Announce Type: cross Abstract: Multi-agent debate systems are typically evaluated only on whether the final answer is correct, overlooking the quality of the intermediate reasoning that debate is designed to produce.

By Ali Keramati, Justin Cheok, Jacob Horne, Mark Warschauer

llms agents nlp

arXiv AI

Aug 5

Where Reasoning Diverges: Localized Multi-Agent Debate for Multi-Hop Question Answering

arXiv:2608. 01463v2 Announce Type: replace Abstract: Multi-agent debate commonly exchanges complete rationales even when disagreements concern only a few intermediate claims.

By Weijun Gao, Xiang Ding, Haoyang Liu, Tiancheng Xing

agents nlp benchmarks

arXiv AI

Jun 16

DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation

arXiv:2601. 05746v2 Announce Type: replace Abstract: Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving.

By Zhenghao Li, Zhi Zheng, Wei Chen, Jielun Zhao, Yong Chen, Tong Xu, Enhong Chen

llms agents benchmarks

One email a morning, machine-written

Related stories

Avoiding Obfuscation with Prover-Estimator Debate

Multi-Agent Debate Strategies: Survey, Taxonomy, and Challenges

Evaluating the Capabilities of LLMs for Persuasive Dialogue

The Confident Liar: Diagnosing Multi-Agent Debate with Log-Probabilities and LLM-as-Judge

Where Reasoning Diverges: Localized Multi-Agent Debate for Multi-Hop Question Answering

DynaDebate: Breaking Homogeneity in Multi-Agent Debate with Dynamic Path Generation