10 papers
Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents
Jiawei Huang, Qingping Yang, Renjie Zheng +1
Despite recent progress in Large Language Model (LLM) Agents for Software Engineering (SWE) tasks, end-to-end fine-tuning typically relies on verifiable terminal rewards such as wh…
CUDA Agent: Large-Scale Agentic RL for High-Performance CUDA Kernel Generation
Weinan Dai, Hanlin Wu, Qiying Yu +13
GPU kernel optimization is fundamental to modern deep learning but remains a highly specialized task requiring deep hardware expertise. Despite strong performance in general progra…
BABE: Biology Arena BEnchmark
Junting Zhou, Jin Chen, Linfeng Hao +10
The rapid evolution of large language models (LLMs) has expanded their capabilities from basic dialogue to advanced scientific reasoning. However, existing benchmarks in biology of…
AetherCode: Evaluating LLMs' Ability to Win In Premier Programming Competitions
Zihan Wang, Jiaze Chen, Zhicheng Liu +25
Competitive programming has emerged as a critical benchmark for evaluating the reasoning and coding capabilities of Large Language Models (LLMs). Despite impressive progress on exi…
Truncated Proximal Policy Optimization
Tiantian Fan, Lingjun Liu, Yu Yue +20
Recently, test-time scaling Large Language Models (LLMs) have demonstrated exceptional reasoning capabilities across scientific and professional tasks by generating long chains-of-…
Enigmata: Scaling Logical Reasoning in Large Language Models with Synthetic Verifiable Puzzles
Jiangjie Chen, Qianyu He, Siyu Yuan +9
Large Language Models (LLMs), such as OpenAI's o1 and DeepSeek's R1, excel at advanced reasoning tasks like math and coding via Reinforcement Learning with Verifiable Rewards (RLVR…