13 papers
Cowork-Gym: Synthesizing Interactive Work Environments at Scale
Anni Zou, Cheng Chen, Jiaji Deng +18
Cowork agents navigate dependencies across tools and files while adapting to changing user requirements and edits to shared workspaces. Scaling such environments requires maintaini…
Towards Robust Tool Use in Agents via Experience-Driven Adaptive Guidance
Can Wang, Haoran Chen, Li Yu +4
The performance bottleneck of agents is increasingly shifting from model capability to the robustness of their execution processes. Tools play a central role as the primary interfa…
From Simple QA to Deep Research: A Verifiable Benchmark Constructed through Iterative Task Evolution
Can Wang, Haoran Chen, Haowen Gao +3
Deep research benchmarks require expert-level tasks and reliable evaluation grounded in task-specific knowledge. Existing benchmarks rely heavily on expert authoring or pre-existin…
AgentJet: A Distributed Swarm Training Framework for Agentic Reinforcement Learning
Qingxu Fu, Boyin Liu, Shuchang Tao +5
Training reinforcement learning (RL) policies for large language model (LLM) agents requires optimizing multi-turn trajectories that interact with external environments. Existing t…
LabOSBench: Benchmarking Computer Use Agents for Scientific Instrument Control
Anqi Zou, Han Deng, Chengyu Zhang +9
Current computer-use benchmarks primarily focus on software operation tasks in virtualized systems, whereas scientific instrumentation scenarios require coordinated control over co…
A Gradient Perspective on RLVR Stability and Winner Advantage Policy Optimization
Prasanth YSS, Zhichen Ren, Rasa Hosseinzadeh +6
Reinforcement learning with verifiable rewards (RLVR) improves language-model reasoning, but GRPO-style optimization remains prone to collapse. We analyse this instability through…
SelfEvoSkill: Paired Execution Audits for Skill Revision without External Outcome Supervision
Haowen Gao, Haoran Chen, Can Wang +5
Agent skills provide LLM agents with reusable procedures, but a given skill may be incomplete, ineffective, or misleading for the current task. Existing methods for revising skills…
SeeUPO: Sequence-Level Agentic-RL with Convergence Guarantees
Tianyi Hu, Qingxu Fu, Yanxi Chen +2
Reinforcement learning (RL) has emerged as the predominant paradigm for training large language model (LLM)-based AI agents. However, existing backbone RL algorithms lack verified…
CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RL
Shinji Mai, Yunpeng Zhai, Ziqian Chen +5
Large language model based agents are increasingly deployed in complex, tool augmented environments. While reinforcement learning provides a principled mechanism for such agents to…
Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
Zouying Cao, Jiaji Deng, Li Yu +4
Procedural memory enables large language model (LLM) agents to internalize "how-to" knowledge, theoretically reducing redundant trial-and-error. However, existing frameworks predom…
AgentEvolver: Towards Efficient Self-Evolving Agent System
Yunpeng Zhai, Shuchang Tao, Cheng Chen +10
Autonomous agents powered by large language models (LLMs) have the potential to significantly enhance human productivity by reasoning, using tools, and executing complex tasks in d…
Auto-Rubric: Learning From Implicit Weights to Explicit Rubrics for Reward Modeling
Lipeng Xie, Sen Huang, Zhuo Zhang +9
Conventional reward modeling relies on gradient descent over neural weights, creating opaque, data-hungry "black boxes." We propose a paradigm shift from implicit to explicit rewar…
Voting with the Graph: Stable RLAIF via Topological Consistency Maximization
Boyin Liu, Zhuo Zhang, Sen Huang +8
Reinforcement Learning from AI Feedback (RLAIF) relies on LLM judges as preference measurement instruments, yet these instruments are fundamentally limited by random measurement er…