10 citations · 14 across the 10 of their papers we have counts for
6 papers · 1 filter
Imitation Learning for Multi-turn LM Agents via On-policy Expert Corrections
Niklas Lauffer, Xiang Deng, Srivatsa Kundurthy +2
A popular paradigm for training LM agents relies on imitation learning, fine-tuning on expert trajectories. However, we show that the off-policy nature of imitation learning for mu…
Robust and Diverse Multi-Agent Learning via Rational Policy Gradient
Niklas Lauffer, Ameesh Shah, Micah Carroll +3
Adversarial optimization algorithms that explicitly search for flaws in agents' policies have been successfully applied to finding robust and diverse policies in multi-agent settin…
SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
Xiang Deng, Jeff Da, Edwin Pan +19
We introduce SWE-Bench Pro, a substantially more challenging benchmark that builds upon the best practices of SWE-BENCH [25], but is explicitly designed to capture realistic, compl…
Provably Correct Automata Embeddings for Optimal Automata-Conditioned Reinforcement Learning
Beyazit Yalcinkaya, Niklas Lauffer, Marcell Vazquez-Chanlatte +1
Automata-conditioned reinforcement learning (RL) has given promising results for learning multi-task policies capable of performing temporally extended objectives given at runtime,…
Multi-Agent Risks from Advanced AI
Lewis Hammond, Alan Chan, Jesse Clifton +41
The rapid development of advanced AI agents and the imminent deployment of many instances of these agents will give rise to multi-agent systems of unprecedented complexity. These s…
Learning Symbolic Task Decompositions for Multi-Agent Teams
Ameesh Shah, Niklas Lauffer, Thomas Chen +2
One approach for improving sample efficiency in cooperative multi-agent learning is to decompose overall tasks into sub-tasks that can be assigned to individual agents. We study th…