5 papers
LieCraft: A Multi-Agent Framework for Evaluating Deceptive Capabilities in Language Models
Matthew Lyle Olson, Neale Ratzlaff, Musashi Hinck +5
Large Language Models (LLMs) exhibit impressive general-purpose capabilities but also introduce serious safety risks, particularly the potential for deception as models acquire inc…
Model-Agnostic Policy Explanations with Large Language Models
Zhang Xi-Jia, Yue Guo, Shufei Chen +4
Intelligent agents, such as robots, are increasingly deployed in real-world, human-centric environments. To foster appropriate human trust and meet legal and ethical standards, the…
Speaking the Language of Teamwork: LLM-Guided Credit Assignment in Multi-Agent Reinforcement Learning
Muhan Lin, Shuyang Shi, Yue Guo +7
Credit assignment, the process of attributing credit or blame to individual agents for their contributions to a team's success or failure, remains a fundamental challenge in multi-…
Symbolic Graph Inference for Compound Scene Understanding
FNU Aryan, Simon Stepputtis, Sarthak Bhagat +4
Scene understanding is a fundamental capability needed in many domains, ranging from question-answering to robotics. Unlike recent end-to-end approaches that must explicitly learn…
Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models
Muhan Lin, Shuyang Shi, Yue Guo +6
The correct specification of reward models is a well-known challenge in reinforcement learning. Hand-crafted reward functions often lead to inefficient or suboptimal policies and m…