The papers

Most central to this idea first, not most recent.

• Independentcs.AI

  Closed-loop development improves mobile agents across planning and tool use

  Sept 2026

• Industrycs.AI

  Co-trained agent roles improve tool-based reasoning and verification

  Waseda University, Adelaide University · Sept 2026

• Chinese Techcs.CLcode

  Self-retiring distillation improves reinforcement learning for multi-turn agents

  Zhejiang University, Alibaba Group · Sept 2026

• Big Techcs.CV

  A single visual agent spans mobile, desktop, web, and tool use

  Apple · Sept 2026

• Top Universitycs.CV

  Reinforcement learning trains video AI agents to use external tools effectively

  Princeton University, Stanford University · Sept 2026

• Industrycs.AI

  Joint training helps small language models create and use tools

  Appier AI Research, National Taiwan University · Aug 2026

• Chinese Techcs.LG

  Shared-prefix training accelerates reinforcement learning for hybrid-attention agents

  Ant Group · Sept 2026

• Big Techcs.LG

  Dense credit assignment from gold-answer log-probabilities improves long-horizon agent RL

  University of Wisconsin–Madison, Microsoft Research · July 2026

• Big Techcs.LG

  A lightweight PyTorch-native framework matches Megatron-based agentic RL training performance.

  NVIDIA · July 2026

• Big Techcs.LG

  Predicting environment observations during fine-tuning improves later agent exploration

  University of Maryland, AWS AI Labs · Sept 2026

• Industrycs.AI

  Synthetic rewards train agents to diagnose simulated advertising anomalies

  Independent Researchers · Sept 2026

• Top Universitycs.AI

  Privileged supervision improves action-level credit for language-model agents

  Zhejiang University · Sept 2026

• Chinese Techcs.LG

  Contrastive branch training improves credit assignment for tool-using language models

  Alibaba Group, Harbin Institute of Technology · Aug 2026

• Top Universitycs.LG

  RL with context compaction trains long-horizon agents

  Tsinghua University · July 2026

• Chinese Techcs.AIcode

  Evolutionary training harness co-evolves with LLM policies for RL

  Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Tongyi Lab , Alibaba Group · June 2026

• Big Techcs.AIcode

  Dynamic rubrics improve credit assignment for long-horizon agent training

  Carnegie Mellon University, IBM Research · Sept 2026

• Industrycs.CR

  Graph-based policy constrains LLM agents for topology-aware incident response

  Indiana University · Sept 2026

• Big Techcs.AI

  New framework lets you train AI agents inside the same harness systems they use at inference

  Columbia University, Dartmouth College · July 2026

• Chinese Techcs.CL

  Separating planning from synthesis improves long-horizon search agents

  Zhejiang University, Tencent · Sept 2026

• Chinese Techcs.CL

  Agents learn to manage long contexts through fine-grained reinforcement learning

  Tsinghua University, Tencent Youtu Lab · Sept 2026

• Independentcs.CLcode

  A 2.8-trillion-parameter open MoE model approaches frontier performance.

  July 2026

• Chinese Techcs.AI

  Three-stage training instills world model planning into LLM agents

  Fudan University, Shanghai Innovation Institute · June 2026

• Independentcs.LG

  Mixed-granularity agent graphs improve collaboration across varied tasks

  Sept 2026

• Chinese Techcs.AI

  Evolving terminal environments keeps training tasks challenging as agents improve

  Hunyuan Team, Tencent · Sept 2026

• Chinese Techcs.CV

  Unified visual-generation agentic model outperforms larger closed-source models

  Tencent Hunyuan, Hong Kong University of Science and Technology · Mar 2026

• Top Universitycs.AI

  Enumerating Tool Choices Beats Sampling Them in Genomic Reasoning

  The Chinese University of Hong Kong, Shenzhen, Shenzhen Future Network of Intelligence Institute (FNii-Shenzhen) · Sept 2026