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…
SkillRouter: Skill Routing for LLM Agents at Scale
YanZhao Zheng, ZhenTao Zhang, Chao Ma +8
Reusable skills let LLM agents package task-specific procedures, tool affordances, and execution guidance into modular building blocks. As skill ecosystems grow to tens of thousand…
Idea2Story: An Automated Pipeline for Transforming Research Concepts into Complete Scientific Narratives
Tengyue Xu, Zhuoyang Qian, Gaoge Liu +16
Autonomous scientific discovery with large language model (LLM)-based agents has recently made substantial progress, demonstrating the ability to automate end-to-end research workf…
MimicDreamer: Aligning Human and Robot Demonstrations for Scalable VLA Training
Haoyun Li, Ivan Zhang, Runqi Ouyang +12
Vision Language Action (VLA) models derive their generalization capability from diverse training data, yet collecting embodied robot interaction data remains prohibitively expensiv…
MathReal: We Keep It Real! A Real Scene Benchmark for Evaluating Math Reasoning in Multimodal Large Language Models
Jun Feng, Zixin Wang, Zhentao Zhang +5
Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in visual mathematical reasoning across various existing benchmarks. However, these benchmarks ar…