Social Cooperation in Conversational AI Agents
On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks
Abstract (arXiv)
The development of AI agents based on large, open-domain language models (LLMs) has paved the way for the development of general-purpose AI assistants that can support human in tasks such as writing, coding, graphic design, and scientific research. A major challenge with such agents is that, by necessity, they are trained by observing relatively short-term interactions with humans. Such models can fail to generalize to long-term interactions, for example, interactions where a user has repeatedly corrected mistakes on the part of the agent. In this work, we argue that these challenges can be overcome by explicitly modeling humans' social intelligence, that is, their ability to build and maintain long-term relationships with other agents whose behavior cannot always be predicted. By mathematically modeling the strategies humans use to communicate and reason about one another over long periods of time, we may be able to derive new game theoretic objectives against which LLMs and future AI agents may be optimized.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 5 of its 8 references that are in the map. First posted on arXiv 2 Jun 2025.
Builds on
5 of 8 references.
References · 5
- 2023Focused Transformer: Contrastive Training for Context Scalingcited by 133
- 2023Large Language Models as Zero-Shot Conversational Recommenderscited by 127
- 2020Toward the Fundamental Limits of Imitation Learningcited by 96
- 2023The Programmer's Assistant: Conversational Interaction with a Large Language Model for Software Developmentcited by 96
- 2021Imitation Learning by Reinforcement Learningcited by 17
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Multi-Agent Language Models: Advancing Cooperation, Coordination, and Adaptation
- 2025Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia
- 2023Exploring Collaboration Mechanisms for LLM Agents: A Social Psychology View
- 2025A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions
- 2024AgentSense: Benchmarking Social Intelligence of Language Agents through Interactive Scenarios
- 2024Shall We Team Up: Exploring Spontaneous Cooperation of Competing LLM Agents
- 2023The Rise and Potential of Large Language Model Based Agents: A Survey
- 2023Exploring the Intersection of Large Language Models and Agent-Based Modeling via Prompt Engineering