5 papers
Policy-Guided Stepwise Model Routing for Cost-Effective Reasoning
Wenwen Si, Insup Lee, Osbert Bastani
Inference-time computation has greatly enhanced the performance of large language models (LLMs) on challenging reasoning tasks, but this strategy can incur high inference costs. On…
RAPID: An Efficient Reinforcement Learning Algorithm for Small Language Models
Lianghuan Huang, Sagnik Anupam, Insup Lee +2
Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms…
RICL: Adding In-Context Adaptability to Pre-Trained Vision-Language-Action Models
Kaustubh Sridhar, Souradeep Dutta, Dinesh Jayaraman +1
Multi-task ``vision-language-action'' (VLA) models have recently demonstrated increasing promise as generalist foundation models for robotics, achieving non-trivial performance out…
Effective Reinforcement Learning for Reasoning in Language Models
Lianghuan Huang, Shuo Li, Sagnik Anupam +2
Reinforcement learning (RL) has emerged as a promising strategy for improving the reasoning capabilities of language models (LMs) in domains such as mathematics and coding. However…
REGENT: A Retrieval-Augmented Generalist Agent That Can Act In-Context in New Environments
Kaustubh Sridhar, Souradeep Dutta, Dinesh Jayaraman +1
Building generalist agents that can rapidly adapt to new environments is a key challenge for deploying AI in the digital and real worlds. Is scaling current agent architectures the…