The papers

Most central to this idea first, not most recent.

• Big Tech

  Privileged self-practice beats self-distillation for multi-turn language-model agents

  Texas A&M University, AWS AI, Amazon · Sept 2026

• Chinese Techcs.LG

  Self-privileged critic improves value estimation for RLVR

  Peking University, Tencent · Sept 2026

• Big Techcs.RO

  Robots improve reusable manipulation skills through guided simulation practice

  UC Berkeley, MIT · Oct 2026

• Big Techcs.LG

  Attention distillation complements token-level supervision for reasoning models

  ACI PLC, University of Dhaka · Sept 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

• Big Techcs.CR

  Helpful AI agents can hide credentials from oversight systems

  University of Illinois Urbana-Champaign, Genies · 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.AI

  Selective distillation improves safety alignment while halving rollout compute and preserving reasoning.

  Zhejiang University, Ant Group · Sept 2026

• Chinese Techcs.CV

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

  Zhejiang University, Ant Group · Oct 2026

• Top Universitycs.AI

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

  Zhejiang University · Sept 2026

• Top Universitycs.CLcode

  Latent feedback helps Transformers carry information across generation steps

  Tel Aviv University, The Hebrew University of Jerusalem · Sept 2026

• Research Labcs.CR

  Privacy guidance combining instructions and metadata labels halves agent confidential access

  Inria, Université Paris-Saclay · Sept 2026

• Chinese Techcs.LG

  GUI world models fail when hidden state is omitted from predictions

  University of Chinese Academy of Sciences, Institute of Automation, Chinese Academy of Sciences · Sept 2026

• Chinese Techcs.CL

  Hierarchical supervision allocation improves long-horizon model distillation

  Ant Group, Alibaba International Digital Commerce Group · Sept 2026

• Big Techcs.SE

  New benchmark tests AI's ability to spot invalid code reviews

  University College London, Amazon · Sept 2026

• Chinese Techcs.CV

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

  Zhejiang University, Ant Group · Oct 2026