Challenge: Multi-agent debate (MAD) aims to improve large language model reasoning by letting multiple agents exchange answers and then aggregate their opinions.
Approach: They propose a principled framework that joins sycophancy and self-bias to mitigate and quantify identity bias in multi-agent debate by removing identity markers from prompts.
Outcome: The proposed framework joins identity-driven sycophancy and self-bias to mitigate and quantify identity bias in multi-agent debate.

Similar Papers

Demystifying Multi-Agent Debate: The Role of Confidence and Diversity (2026.findings-acl)

Copied to clipboard

Challenge: Multi-agent debate (MAD) is widely used to improve large language models' (LLMs) reasoning and test-time scaling.
Approach: They propose a diversity-aware initialisation that selects a more diverse pool of candidate answers, increasing the likelihood that a correct hypothesis is present at the start of debate.
Outcome: The proposed protocol outperforms vanilla MAD and majority vote on six reasoning-oriented QA benchmarks.
Free-MAD: Consensus-Free Multi-Agent Debate (2026.findings-acl)

Copied to clipboard

Challenge: Existing multi-agent debate methods rely on multiple rounds of interaction among agents to reach consensus, and the final output is decided by majority voting in the last round.
Approach: They propose a multi-agent debate framework that eliminates the need for consensus among agents and reconstructs the debate phase by introducing anti-conformity.
Outcome: Experiments on eight benchmark datasets show that Free-MAD significantly improves reasoning performance while requiring only a single-round debate and thus reducing token costs.
Judging with Many Minds: Do More Perspectives Mean Less Prejudice? On Bias Amplification and Resistance in Multi-Agent Based LLM-as-Judge (2025.findings-emnlp)

Copied to clipboard

Challenge: LLM-as-Judge frameworks provide scalable alternative to human evaluation . but the question of how intrinsic biases manifest in these settings remains unexplored .
Approach: They conduct systematic analysis of four bias types in multi-agent LLM-as-Judge frameworks . they find debate framework amplifies biases sharply after initial debate .
Outcome: The proposed frameworks amplify biases after debate and show they are stronger in meta-judge scenarios.
S2-MAD: Breaking the Token Barrier to Enhance Multi-Agent Debate Efficiency (2025.naacl-long)

Copied to clipboard

Challenge: Large language models exhibit limitations when handling complex mathematical reasoning and logical inference tasks.
Approach: They propose a sparsification strategy to reduce token costs within Multi-agent Debate (MAD) this strategy minimizes ineffective exchanges of information and unproductive discussions among agents .
Outcome: The proposed approach reduces token costs by up to 94.5% while maintaining performance degradation below 2.0%.
CONSENSAGENT: Towards Efficient and Effective Consensus in Multi-Agent LLM Interactions Through Sycophancy Mitigation (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in multi-agent large language model systems have shown remarkable performance in tasks such as reasoning, planning, and decision-making.
Approach: They propose a framework that dynamically refines prompts based on agent interactions to mitigate sycophancy by requiring additional debate rounds to reach consensus.
Outcome: The proposed framework outperforms both single-agent and multi-a agent baselines and achieves state-of-the-art results across all benchmark datasets.
Advancing Oversight Reasoning across Languages for Audit Sycophantic Behaviour via X-Agent (2025.emnlp-main)

Copied to clipboard

Challenge: Large language models have demonstrated capabilities that are satisfactory to a wide range of users by adapting to their culture and wisdom.
Approach: They propose an Oversight Reasoning framework that audits human–LLM dialogues, reasons about them, captures sycophancy and corrects the final outputs.
Outcome: The proposed framework detects sycophancy, reduces unwarranted agreement and improves cross-turn consistency across different scenarios and languages.
Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy (2026.acl-long)

Copied to clipboard

Challenge: Recent studies have identified a critical drawback of aligning models with human judgments and outputs that are flawed or incorrect.
Approach: They evaluate a range of LLMs to examine whether CoT reasoning mitigates sycophancy . they find that reasoning masks a tendency to scophage in some cases .
Outcome: The proposed model models show that CoT reasoning reduces sycophancy but masks it in some cases.
Enhancing Multi-Agent Debate System Performance via Confidence Expression (2025.findings-emnlp)

Copied to clipboard

Challenge: Multi-Agent Debate systems leverage multiple LLMs to improve task performance.
Approach: They propose to integrate confidence expression into MAD systems to help LLMs communicate their confidence levels.
Outcome: The proposed approach improves debate effectiveness and overall system performance by integrating confidence expression into MAD systems.
Bias in the Mirror : Are LLMs opinions robust to their own adversarial attacks (2025.acl-long)

Copied to clipboard

Challenge: Existing work on large language models lacks robustness, highlighting the limitations of such models.
Approach: They propose a novel approach where two LLMs engage in self-debate to persuade a neutral version of the model.
Outcome: The proposed approach examines whether large language models are robust during interactions and whether they are susceptible to reinforcing misinformation or shifting to harmful viewpoints.
An Empirical Study of Group Conformity in Multi-Agent Systems (2025.findings-acl)

Copied to clipboard

Challenge: Recent advances in Large Language Models (LLMs) have enabled multi-agent systems that simulate real-world interactions with near-human reasoning.
Approach: They analyze how LLM agents shape public opinion through debates on five contentious topics by simulating over 2,500 debates.
Outcome: The proposed models show that LLM agents adopt specific stances over time and align with numerically dominant groups or more intelligent agents, exerting a greater influence.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations