When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning (2026.acl-long)
Copied to clipboard
| 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
Chiyu Ma, Enpei Zhang, Yilun Zhao, Wenjun Liu, Yaning Jia, Peijun Qing, Lin Shi, Arman Cohan, Yujun Yan, Soroush Vosoughi
| 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
Yuting Zeng, Weizhe Huang, Lei Jiang, Tongxuan Liu, XiTai Jin, Chen Tianying Tiana, Jing Li, Xiaohua Xu
| 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. |