10 papers
PAC: Progress-Augmented Advantage Curriculum for Multi-Task Reinforcement Learning of LLMs
Yuanqiang Yu, Yanzhao Zheng, Zhentao Zhang +8
Reinforcement learning (RL) is used to improve the reasoning abilities of LLMs, while training data span heterogeneous tasks. However, most RL post-training pipelines rely on fixed…
LQCDMaster: Agentic Scientific Computing for Lattice Quantum Chromodynamics Research
Haofei Gao, Tingjia Miao, Wenkai Jin +12
Lattice quantum chromodynamics (LQCD) provides a first-principles framework for computing hadronic observables, but its practical use remains limited by the substantial expertise r…
SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents
Yifan Zhou, Zhentao Zhang, Ziming Cheng +8
As LLM agents are increasingly built around reusable skills, a central challenge is no longer only whether agents can use provided skills, but whether they can generate correct, re…
Rubrics to Tokens: Bridging Response-level Rubrics and Token-level Rewards in Instruction Following Tasks
Tianze Xu, Yanzhao Zheng, Pengrui Lu +11
Rubric-based Reinforcement Learning (RL) has emerged as a promising approach for aligning Large Language Models (LLMs) with complex, open-domain instruction following tasks. Howeve…
ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents
Yong Wu, YanZhao Zheng, TianZe Xu +9
LLM-based agents show strong potential for long-horizon reasoning, yet their context size is limited by deployment factors (e.g., memory, latency, and cost), yielding a constrained…
Story2Proposal: A Scaffold for Structured Scientific Paper Writing
Zhuoyang Qian, Wei Shi, Xu Lin +19
Generating scientific manuscripts requires maintaining alignment between narrative reasoning, experimental evidence, and visual artifacts across the document lifecycle. Existing la…