paper-with-me

Papers

Super-additive Cooperation in Language Model Agents

2025-08-21 · Filippo Tonini, Lukas Galke arxiv

With the prospect of autonomous artificial intelligence (AI) agents, studying their tendency for cooperative behavior becomes an increasingly relevant topic. This study is inspired by the super-additive cooperation theory, where the combined effects of repeated interactions and inter-group rivalry have been argued to be the cause for cooperative tendencies found in humans. We devised a virtual tournament where language model agents, grouped into teams, face each other in a Prisoner's Dilemma game. By simulating both internal team dynamics and external competition, we discovered that this blend substantially boosts both overall and initial, one-shot cooperation levels (the tendency to cooperate in one-off interactions). This research provides a novel framework for large language models to strategize and act in complex social scenarios and offers evidence for how intergroup competition can, counter-intuitively, result in more cooperative behavior. These insights are crucial for designing future multi-agent AI systems that can effectively work together and better align with human values. Source code is available at https://github.com/pippot/Superadditive-cooperation-LLMs.

📄 PDF Abstract BibTeX arXiv:2508.15510

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Multi-Agent, Human-Agent and Beyond: A Survey on Cooperation in Social Dilemmas

2024-02-27 · Chunjiang Mu, Hao Guo, Yang Chen, Chen Shen 외

The study of cooperation within social dilemmas has long been a fundamental topic across various disciplines, including computer science and social science. Recent advancements in Artificial Intelligence (AI) have signif…

Safe and Interpretable Multimodal Path Planning for Multi-Agent Cooperation

2026-02-22 · Haojun Shi, Suyu Ye, Katherine M. Guerrerio, Jianzhi Shen 외 arxiv

Successful cooperation among decentralized agents requires each agent to quickly adapt its plan to the behavior of other agents. In scenarios where agents cannot confidently predict one another's intentions and plans, la…

Autonomous DrivingProgram Synthesis

VIKI-R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning

2025-06-10 · Li Kang, Xiufeng Song, Heng Zhou, Yiran Qin 외

Coordinating multiple embodied agents in dynamic environments remains a core challenge in artificial intelligence, requiring both perception-driven reasoning and scalable cooperation strategies. While recent works have l…

Task PlanningVisual Reasoning

Overcoming the Machine Penalty with Imperfectly Fair AI Agents

2024-09-29 · Zhen Wang, Ruiqi Song, Chen Shen, Shiya Yin 외

Despite rapid technological progress, effective human-machine cooperation remains a significant challenge. Humans tend to cooperate less with machines than with fellow humans, a phenomenon known as the machine penalty. H…

Tool-RoCo: An Agent-as-Tool Self-organization Large Language Model Benchmark in Multi-robot Cooperation

2025-11-26 · Ke Zhang, Xiaoning Zhao, Ce Zheng, Jiahong Ning 외 arxiv

This study proposes Tool-RoCo, a novel benchmark for evaluating large language models (LLMs) in long-term multi-agent cooperation based on RoCo, a multi-robot cooperative benchmark. Recent research on LLM-based multi-age…