4 papers
Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting
Michael Y. Hu, Benjamin Van Durme, Jacob Andreas +1
Language model (LM) agents deployed in novel environments often exhibit poor sample efficiency when learning from sequential interactions. This significantly hinders the usefulness…
Steering Large Language Models between Code Execution and Textual Reasoning
Yongchao Chen, Harsh Jhamtani, Srinagesh Sharma +2
While a lot of recent research focuses on enhancing the textual reasoning capabilities of Large Language Models (LLMs) by optimizing the multi-agent framework or reasoning chains,…
LM Agents for Coordinating Multi-User Information Gathering
Harsh Jhamtani, Jacob Andreas, Benjamin Van Durme
This paper introduces PeopleJoin, a benchmark for evaluating LM-mediated collaborative problem solving. Given a user request, PeopleJoin agents must identify teammates who might be…
Towards Robust Evaluation of Unlearning in LLMs via Data Transformations
Abhinav Joshi, Shaswati Saha, Divyaksh Shukla +4
Large Language Models (LLMs) have shown to be a great success in a wide range of applications ranging from regular NLP-based use cases to AI agents. LLMs have been trained on a vas…