The papers

Most central to this idea first, not most recent.

• Big Techcs.AI

  Training agents around decisive errors improves prevention and recovery

  Princeton University, NVIDIA · Oct 2026

• Chinese Techcs.CL

  Teacher-guided training improves specialization and coordination in multi-agent models

  University of Science and Technology of China, Tencent · Sept 2026

• Chinese Techcs.CL

  Hierarchical supervision allocation improves long-horizon model distillation

  Ant Group, Alibaba International Digital Commerce Group · Sept 2026

• Chinese Techcs.LGcode

  Token-level teacher routing beats prompt-level routing in multi-teacher distillation

  Shanghai Jiao Tong University, GAIR · Sept 2026

• Chinese Techcs.LG

  Agent distillation improves when supervision follows outcomes, not model disagreement

  Qwen Large Model Application Team, Alibaba, Peking University · Sept 2026

• Chinese Techcs.LG

  Execution graph helps off-the-shelf teachers supervise student agents better

  Yuanbao Team, Tencent, Tsinghua University · Sept 2026

• Chinese Techcs.LG

  Online distillation cuts needless verbosity in RL-trained models

  ByteDance Seed, Tongji University · Oct 2026

• Chinese Techcs.LG

  Ablating individual constraints improves distillation for complex instruction following

  Alibaba Group · Sept 2026

• Big Techcs.LG

  Attention distillation complements token-level supervision for reasoning models

  ACI PLC, University of Dhaka · Sept 2026

• Big Tech

  Co-evolving teacher and student models improves mathematical reasoning

  Meta AI, University of California, Riverside · Sept 2026

• Chinese Techcs.CV

  Real-time GUI feedback improves training for computer-use agents

  Zhejiang University, Ant Group · Oct 2026

• Chinese Techcs.AI

  Self-distillation trains GUI agents for longer, memory-dependent tasks

  Institute of Information Engineering, Chinese Academy of Sciences, Tencent · Sept 2026

• Chinese Techcs.CV

  Real-time GUI feedback improves training for computer-use agents

  Zhejiang University, Ant Group · Oct 2026

• Chinese Techcs.LG

  Training agents on their own trajectories accelerates reward-based learning

  Zhejiang University, Ant Healthcare · Oct 2026

• Top Universitycs.CLcode

  Distillation Before Reinforcement Learning Improves Reasoning Model Post-Training

  New York University, University of Chicago · Sept 2026

• Chinese Techcs.CL

  Terminal agents verify often but miss and mishandle many errors

  Northeastern University, Inclusion AI, Ant Group · Oct 2026

• Chinese Techcs.AI

  PlanGuard detects physical risks across complete embodied-agent plans

  Anhui Province Key Laboratory of Digital Security, The University of Hong Kong · Sept 2026