4 papers · 1 filter
When "Correct" Is Not Safe: Can We Trust Functionally Correct Patches Generated by Code Agents?
Yibo Peng, James Song, Lei Li +6
Code agents are increasingly trusted to autonomously fix bugs on platforms such as GitHub, yet their security evaluation focuses almost exclusively on functional correctness. In th…
RLBoost: Harvesting Preemptible Resources for Cost-Efficient Reinforcement Learning on LLMs
Yongji Wu, Xueshen Liu, Haizhong Zheng +5
Reinforcement learning (RL) has become essential for unlocking advanced reasoning capabilities in large language models (LLMs). RL workflows involve interleaving rollout and traini…
Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation
Xinyu Yang, Yuwei An, Hongyi Liu +2
Autoregressive Large Language Models (AR-LLMs) frequently exhibit implicit parallelism in sequential generation. Inspired by this, we introduce Multiverse, a new generative model t…
APE: Faster and Longer Context-Augmented Generation via Adaptive Parallel Encoding
Xinyu Yang, Tianqi Chen, Beidi Chen
Context-augmented generation (CAG) techniques, including RAG and ICL, require the efficient combination of multiple contexts to generate responses to user queries. Directly inputti…