1 citations · 1 across the 15 of their papers we have counts for
7 papers · 1 filter
Rubric Dropout: A Simple Way to Mitigate Reward Hacking in Rubric-Based RL
Minglai Yang, Xinyu Guo, Zhengliang Shi +8
Rubric-based reinforcement learning, in which an LLM judge scores responses against prompt-specific criteria, has become a standard way to post-train language models on tasks witho…
SWE-INTERACT: Reimagining SWE Benchmarks as User-Driven Long-Horizon Coding Sessions
Mohit Raghavendra, Anisha Gunjal, Aakash Sabharwal +1
We introduce SWE-Interact, a new testbed for evaluating coding agents on multi-turn, interactive, user-driven software engineering tasks. Existing frontier SWE benchmarks typically…
Rubric-Guided Self-Distillation: Post-Training Without Rubric Verifiers
MohammadHossein Rezaei, Anas Mahmoud, Zihao Wang +6
Rubrics have emerged as an alternative to RLVR in open-ended domains where a single ground-truth final answer is not available. Existing rubric-based training methods rely on an LL…
SWE Atlas: Benchmarking Coding Agents Beyond Issue Resolution
Mohit Raghavendra, Soham Dan, Miguel Romero Calvo +12
We introduce SWE Atlas, a benchmark suite for coding agents spanning three professional software engineering workflows: Codebase Q&A (124 tasks), Test Writing (90 tasks), and Refac…
Agentic Rubrics as Contextual Verifiers for SWE Agents
Mohit Raghavendra, Anisha Gunjal, Bing Liu +1
Verification is critical for improving agents: it provides the reward signal for Reinforcement Learning and enables inference-time gains through Test-Time Scaling (TTS). Despite it…
TutorBench: A Benchmark To Assess Tutoring Capabilities Of Large Language Models
Rakshith S Srinivasa, Zora Che, Chen Bo Calvin Zhang +11
As students increasingly adopt large language models (LLMs) as learning aids, it is crucial to build models that are adept at handling the nuances of tutoring: they need to identif…
Chasing the Tail: Effective Rubric-based Reward Modeling for Large Language Model Post-Training
Junkai Zhang, Zihao Wang, Lin Gui +7
Reinforcement fine-tuning (RFT) often suffers from reward over-optimization, where a policy model hacks the reward signals to achieve high scores while producing low-quality output…