Talk, Judge, Cooperate: Gossip-Driven Indirect Reciprocity in Self-Interested LLM Agents

Shuhui Zhu, Yue Lin, Shriya Kaistha, Wenhao Li, Baoxiang Wang, Hongyuan Zha, Gillian K Hadfield, Pascal Poupart
Working Paper
Paper

We introduce public gossip as a decentralized reputation mechanism that enables self-interested LLM agents to cooperate in mixed-motive settings. Building on this idea, our ALIGN framework uses open-ended gossip to assess trustworthiness, sustain reciprocity, and reliably exclude defectors.

Information Bargaining: Bilateral Commitment in Bayesian Persuasion

Yue Lin, Shuhui Zhu, William A Cunningham, Wenhao Li, Pascal Poupart, Hongyuan Zha, Baoxiang Wang
Working Paper
Paper

This paper reframes Bayesian persuasion as an information bargaining problem to address its complexity in long-term interactions. Unlike one-sided commitment models, the proposed framework enables fairer and more efficient cooperation by balancing the sender's and receiver's roles. Empirical validation using LLMs confirms the framework’s predictions.

Learning to Negotiate via Voluntary Commitment

Shuhui Zhu, Baoxiang Wang, Sriram Ganapathi Subramanian, Pascal Poupart
AISTATS, 2025
Paper | Code | Talk | Poster

We present a novel framework where agents can voluntarily commit to actions in strategic interactions, improving cooperation in mixed-motive environments.

Altared Environments: The Role of Normative Infrastructure in AI Alignment

Rakshit Trivedi, Nikhil Chandak, Andrei Ioan Muresanu, Shuhui Zhu, Atrisha Sarkar, Joel Z Leibo, Dylan Hadfield-Menell, Gillian K Hadfield
Submitted to ICLR, 2024
Paper

We propose Altared Games, a novel Markov game framework integrating a classification institution to enable AI agents to adapt to dynamic norms, demonstrating its effectiveness in enhancing cooperation and social welfare in multi-agent reinforcement learning environments.

Bayesian Persuasion Is a Bargaining Game

Yue Lin, Shuhui Zhu, William A Cunningham, Wenhao Li, Pascal Poupart, Hongyuan Zha, Baoxiang Wang
Submitted to ICLR, 2024
Paper

We reformulate Bayesian persuasion as a bargaining game, demonstrating that the receiver can leverage strategic commitments to counteract the sender’s informational advantage, and validate this perspective through theoretical analysis and empirical experiments with large language models, which exhibit bargaining behaviors in persuasion tasks.

Spline Parameterization for Continuous Normalizing Flows

Shuhui Zhu
Master's Thesis, 2021
Thesis

I develop a Spline-based parameterization method for Continuous Normalizing Flows using Neural ODEs, formulating the problem as an optimal control task to efficiently learn time-dependent patterns while reducing computational cost and maintaining accuracy.