6 papers
MATES: Learning Multi-Agent Interactions by Transforming Observations for Frozen Single-Agent Policies
Elie Abboud, Oren Gal
Multi-agent reinforcement learning (MARL) commonly trains decentralized policies from scratch, requiring agents to acquire individual task competence and coordination simultaneousl…
Learning at the Right Pace: Adaptive Data Scheduling Improves LLM Reinforcement Learning
Zicheng Xu, Ruixuan Zhang, Yu-Neng Chuang +7
Large Language Models (LLMs) achieve remarkable reasoning capabilities through reinforcement learning (RL) post-training. However, existing RL post-training commonly relies on unif…
ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning
Elie Abboud, Oren Gal
Sparse rewards are a major bottleneck in multi-agent reinforcement learning (MARL), where simultaneous learning induces non-stationarity and makes reward design especially delicate…
MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
Jonathan Steinberg, Oren Gal
Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The challenge is structural: existing…
Semantic Denial of Service in LLM-controlled robots
Jonathan Steinberg, Oren Gal
Safety-oriented instruction-following is supposed to keep LLM-controlled robots safe. We show it also creates an availability attack surface. By injecting short safety-plausible ph…
Learning to Explore Indoor Environments using Autonomous Micro Aerial Vehicles
Yuezhan Tao, Eran Iceland, Beiming Li +7
In this paper, we address the challenge of exploring unknown indoor aerial environments using autonomous aerial robots with Size Weight and Power (SWaP) constraints. The SWaP const…