5 papers
Prism-GRPO: Faster VLA Policy Optimization via Splitting Same-outcome Groups
Zeyun Deng, Yuzhe Lu, Yawei Wang +6
GRPO is increasingly used for reinforcement learning of vision-language-action (VLA) policies because, unlike PPO, it does not require training a critic. This simplification comes…
Consilience for Verifier-Free Test-Time Scaling
Lecheng Kong, Like Hui, Haitao Mao +1
Test-time scaling often uses an external verifier, such as compilers and test cases in coding or trained value functions in robotics applications, to obtain high-quality rollouts.…
MigrationBench: Repository-Level Code Migration Benchmark from Java 8
Linbo Liu, Xinle Liu, Qiang Zhou +8
With the rapid advancement of powerful large language models (LLMs) in recent years, a wide range of software engineering tasks can now be addressed using LLMs, significantly enhan…
MURPHY: Feedback-Aware GRPO with Retrospective Credit Assignment for Multi-Turn Code Generation
Chanakya Ekbote, Vijay Lingam, Sujay Sanghavi +4
Reinforcement Learning with Verifiable Rewards (RLVR) has become a standard recipe for post-training LLMs on reasoning tasks, with Group Relative Policy Optimization (GRPO) emergin…
Lossless Token Sequence Compression via Meta-Tokens
John Harvill, Ziwei Fan, Hao Wang +4
Existing work on prompt compression for Large Language Models (LLM) focuses on lossy methods that try to maximize the retention of semantic information that is relevant to downstre…