Renmin University of China · 13 records

dateidtitleauthorsvenue↑
2026-11-032611.05036ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon AgentsGuanting Dong et al.arXiv39
2026-11-022611.03178CoworkOS:Scaling Agent Coworkers for Real-world AutomationJiajie Jin et al.arXiv95
2026-10-222610.29458Harness Scaling for Generalizable Agentic Reinforcement LearningFei Bai et al.arXiv23
2026-10-152610.20256Long-Horizon RL Needs MuonKai Ruan et al.arXiv19
2026-10-122609.36641Inducing Process Supervision from Outcome-Only Reinforcement LearningShengda Fan et al.arXiv14
2026-10-082609.39306ReSAIL: Mitigating Collapse in Iterative Agent Self-DistillationShengjie Jin et al.arXiv30
2026-10-052609.39394Can Computation from Earlier Problems Help LLMs Solve New Ones?Jipei He et al.arXiv4
2026-10-012609.38426LoopVL: Recurrent Visual IntelligenceZhe Qian et al.arXiv47
2026-09-252609.28416Agent-Editing World Model: Rethinking World Modeling for LLM AgentsShuang Sun et al.arXiv41
2026-08-182608.16798ClawGym II: Exploring Black-Box RL on Agent HarnessHuatong Song et al.arXiv42
2026-08-102608.01310FATE: Frame-Level Audio-Visual Temporal EmbeddingKaisi Guan et al.arXiv4
2026-08-052608.04007TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated ReasoningChangle Qu et al.arXiv7
2026-05-292605.29861Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report GenerationChenghao Zhang et al.arXiv10