12 papers
Anchored Self-Play for Code Repair
Caroline Choi, Zeyneb Kaya, Shirley Wu +3
Code repair is an important capability for language models (LMs): given a buggy program and unit tests, an LM must produce a fixed program that passes the tests. Because code repai…
SWE-Together: Evaluating Coding Agents in Interactive User Sessions
Yifan Wu, Zhuokai Zhao, Songlin Li +8
Most coding-agent benchmarks are static: an agent receives a complete task description up front and is judged only by its final code. Real coding assistance is interactive, with us…
Found in Conversation: LLMs Teach Themselves to Close the Multi-Turn Gap
Tianlang Chen, Shirley Wu, Jure Leskovec
Large Language Model (LLM) interactions are typically underspecified, with users clarifying all necessary details across multiple conversational turns. Yet recent work shows that L…
Reflections and New Directions for Human-Centered Large Language Models
Caleb Ziems, Dora Zhao, Rose E. Wang +55
Large Language Models (LLMs) are increasingly shaping the private and professional lives of users, with numerous applications in business, education, finance, healthcare, law, and…
Poly-EPO: Training Exploratory Reasoning Models
Ifdita Hasan Orney, Jubayer Ibn Hamid, Shreya S Ramanujam +5
Exploration is a cornerstone of learning from experience: it enables agents to find solutions to complex problems, generalize to novel ones, and scale performance with test-time co…
SteerVLA: Steering Vision-Language-Action Models in Long-Tail Driving Scenarios
Tian Gao, Celine Tan, Catherine Glossop +8
A fundamental challenge in autonomous driving is the integration of high-level, semantic reasoning for long-tail events with low-level, reactive control for robust driving. While l…