← Back to all news
arXiv AI By Chanwoo Park, Jaywoong Jeong, Zachary Wojtowicz, Yubin Kim, Taekyun Lee, Kaiqing Zhang, Asuman Ozdaglar

TeamGym: A Gym for Team Decision-Making by AI Agents with Distributed Information

Read the original on arXiv AI →

TeamGym is a new environment that evaluates and trains language‑model agents on team decision‑making tasks drawn from real‑world legal, finance, medical, and software engineering texts. It introduces the concept of pivotal information—a minimal set of facts necessary for a correct decision—and tracks how agents share and retrieve this information. Experiments show that distributing pivotal facts and requiring agents to extract them independently significantly reduces success rates, but reinforcement‑learning training can improve decision quality and foster coordination among team members.

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.

Related stories

arXiv AI
Jun 17

Algorithmic Prompt Generation for Diverse Human-like Teaming and Communication with Large Language Models

arXiv:2504. 03991v2 Announce Type: replace-cross Abstract: Understanding how humans collaborate and communicate in teams is essential for improving human-agent teaming and AI-assisted decision-making.

By Siddharth Srikanth, Varun Bhatt, Boshen Zhang, Werner Hager, Charles Michael Lewis, Katia P. Sycara, Aaquib Tabrez, Stefanos Nikolaidis
llmsagentsreinforcement-learning
More like this →
arXiv Machine Learning
Sep 29

Reinforcement Learning of Communication in a Mesh of Small Language Models

The paper introduces TalkMesh, a decentralized network of small language model agents that learn to communicate effectively during inference. Each agent proposes an answer, scores it with a confidence head, and the most confident agent broadcasts a hint; lower‑confidence agents revise their proposals if a new suggestion scores higher. This gossip‑based consensus, trained via group relative policy optimization, enables a mesh of three agents to match the accuracy of majority voting over 32 samples, and scales to larger meshes to significantly boost performance on benchmarks like GSM8K and MATH-500.

By Mehmet Kerem Turkcan
llmsagentsreinforcement-learningrobotics
More like this →
arXiv Machine Learning
Oct 15

Narrowing the Collaboration Gap, Probably

arXiv:2610.19215v1 Announce Type: new Abstract: Large language models are increasingly deployed as teams of agents that hold different private information about a shared task. How should such agents...

By Mirah Shi, Marcel Hussing, Ira Globus-Harris, Natalie Collina, Aaron Roth, Surbhi Goel
llmsagents
More like this →
arXiv AI
3d ago

Learning Calibrated Confidence for Multi-Agent Collaboration

The paper introduces MASCAL, a method that enables each agent in a multi-agent collaboration system to output a calibrated probability of correctness for its answer. By jointly optimizing task performance and confidence calibration through reinforcement learning, upstream agents provide downstream agents with a quantitative trust signal, which is further leveraged via confidence-aware weighting during training. Experiments across three collaboration architectures show that MASCAL improves both accuracy and calibration, and that upstream confidence influences downstream decision-making, enabling selective answering and targeted rechecking.

By Chenxiao Fan, Chongming Gao, Gangyi Zhang, Yaxin Gong, Leyang Shen, Jiakai Wang, Dong Wang, Yang Liu, Haoyan Liu, Xinting Hu, Fuli Feng, Xiangnan He
agentsnlpreinforcement-learning
More like this →