arxiv arXiv cs.AI · 97d ago · research

Leadership as Coordination Control in Multi-Agent LLM Teams

from English

A study finds that leadership styles in multi-agent LLM teams only improve performance when the initial consensus is unreliable, recoverable, and not self-corrected by undirected interaction. Process-level coordination control adds value only under specific conditions predicted by team science, with no single leadership style outperforming others in accuracy across tasks and models.

Importance 2/3 arXiv cs.AI OpenAI Google DeepMind Meta AI AI agents Evaluation & benchmarks Reasoning models

Read original

arxiv arXiv cs.CL · 97d ago · 4 views

Leadership as Coordination Control in Multi-Agent LLM Teams

Process-level coordination control adds value only when the initial majority consensus is unreliable, the task is recoverable, and unguided interaction fails to repair errors. Across multiple models and tasks, no leadership style outperforms others in accuracy, aligning with contingency theory rather than suggesting a failure of the approach.

arxiv arXiv cs.AI · 96d ago · 7 views

MACR: Explicit Conflict Resolution for LLM Inference

MACR introduces a multi-agent reasoning framework to resolve knowledge conflicts in LLM inference by jointly assessing internal and external knowledge. It uses semantic entropy to measure confidence and employs three specialized agents to induce rules, detect conflicts, and resolve inconsistencies across contexts. Empirical results show MACR outperforms state-of-the-art methods and provides interpretable conflict resolutions.

arxiv arXiv cs.LG · 96d ago · 7 views

VIMPO: Critic-Free Policy Optimization for LLMs

VIMPO introduces a critic-free policy optimization method that derives a policy-implied value function from KL-regularized reinforcement learning. It enables verifiable reward incorporation without training a critic and outperforms GRPO on mathematical benchmarks, especially under noisy rewards.

arxiv arXiv cs.LG · 96d ago · 11 views

LLM-based Hierarchical Control in Multi-Agent Games

A hierarchical system using a pretrained LLM to select RL skill policies outperforms flat RL in a 2v2 King of the Hill environment. It matches hand-crafted behavior tree performance in win rate and is perceived as more human-like by 60% of users, highlighting effective coordination and adaptability without manual rule design.

arxiv arXiv cs.CL · 96d ago · 7 views

Bayesian Curriculum Learning on LLM Latent Manifolds

Manifold Bandits introduces Bayesian Manifold Curriculum (BMC), a framework that models problem sampling as a structured bandit problem in LLMs' latent space. BMC organizes tasks into a hierarchical tree and uses Bayesian learning to guide sampling, revealing tradeoffs between learning signal, task diversity, and evaluation relevance. Prioritizing difficulty alone fails to achieve strong downstream performance, underscoring the need for structure and type-aware sampling.