8 papers
Inductive Feedback for Mixed-Policy Distillation
Amir Moeini, Huaijiang Zhu, Daniel Havir +1
Verbal feedback can identify errors and prescribe corrections, providing rich supervision for language-model post-training even when reliable programmatic verifiers are unavailable…
Latent Q-Barrier Shielding for Safe In-Context Reinforcement Learning
Minjae Kwon, Amir Moeini, Shangtong Zhang +1
Safe in-context reinforcement learning (ICRL) adapts online from interaction history without test-time parameter updates while controlling episode cost under a safety budget. Under…
MathlibLemma: Folklore Lemma Generation and Benchmark for Formal Mathematics
Xinyu Liu, Zixuan Xie, Amir Moeini +5
While the ecosystem of Lean and Mathlib has enjoyed celebrated success in formal mathematical reasoning with the help of large language models (LLMs), the absence of many folklore…
Prompt-Driven Domain Adaptation for End-to-End Autonomous Driving via In-Context RL
Aleesha Khurram, Amir Moeini, Shangtong Zhang +1
Despite significant progress and advances in autonomous driving, many end-to-end systems still struggle with domain adaptation (DA), such as transferring a policy trained under cle…
Safe In-Context Reinforcement Learning
Amir Moeini, Minjae Kwon, Alper Kamil Bozkurt +4
In-context reinforcement learning (ICRL) is an emerging RL paradigm where an agent, after pretraining, can adapt to out-of-distribution test tasks without any parameter updates, in…
Reward Is Enough: LLMs Are In-Context Reinforcement Learners
Kefan Song, Amir Moeini, Peng Wang +4
Reinforcement learning (RL) is a framework for solving sequential decision-making problems. In this work, we demonstrate that, surprisingly, RL emerges during the inference time of…
A Survey of In-Context Reinforcement Learning
Amir Moeini, Jiuqi Wang, Jacob Beck +4
Reinforcement learning (RL) agents typically optimize their policies by performing expensive backward passes to update their network parameters. However, some agents can solve new…
Mathador-LM: A Dynamic Benchmark for Mathematical Reasoning on Large Language Models
Eldar Kurtic, Amir Moeini, Dan Alistarh
We introduce Mathador-LM, a new benchmark for evaluating the mathematical reasoning on large language models (LLMs), combining ruleset interpretation, planning, and problem-solving…