5 papers
Knowledge-Centric Self-Improvement
Xuefei Julie Wang, Lauren Hyoseo Yoon, Chengrui Qu +4
Self-improving AI systems typically treat the agent as the object that improves, by optimizing prompts, workflows, harnesses, or even the agent's own code. This agent-centric view…
Training Generalizable Collaborative Agents via Strategic Risk Aversion
Chengrui Qu, Yizhou Zhang, Nicolas Lanzetti +1
Many emerging agentic paradigms require agents to collaborate with one another (or people) to achieve shared goals. Unfortunately, existing approaches to learning policies for such…
Distributionally Robust Cooperative Multi-Agent Reinforcement Learning via Robust Value Factorization
Chengrui Qu, Christopher Yeh, Kishan Panaganti +2
Cooperative multi-agent reinforcement learning (MARL) commonly adopts centralized training with decentralized execution, where value-factorization methods enforce the individual-gl…
Understanding Agent Scaling in LLM-Based Multi-Agent Systems via Diversity
Yingxuan Yang, Chengrui Qu, Muning Wen +5
LLM-based multi-agent systems (MAS) have emerged as a promising approach to tackle complex tasks that are difficult for individual LLMs. A natural strategy is to scale performance…
SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer
Yarden As, Chengrui Qu, Benjamin Unger +6
Deploying reinforcement learning (RL) safely in the real world is challenging, as policies trained in simulators must face the inevitable sim-to-real gap. Robust safe RL techniques…