The papers

Most central to this idea first, not most recent.

• Big Techcs.AI

  Adaptive training curricula produce stronger optimized agent harnesses

  POSTECH, KAIST · Oct 2026

• Top Universitycs.LG

  Fisher-Rao prompt curricula make GRPO training more rollout-efficient

  University of Wisconsin–Madison, University of Washington · Sept 2026

• Big Techcs.AI

  Adaptive instruction selection helps language models learn from peers

  University of Washington, Amazon · Oct 2026

• Academiccs.LG

  Curriculum training exposes prompt injection flaws in frontier language models

  The Pennsylvania State University, Purdue University · Sept 2026

• Independentcs.AI

  Skill-guided environment synthesis improves post-training for tool-using agents

  Sept 2026

• Top Universitycs.AI

  Self-play on generated programs produces transferable language-model capabilities

  Independent Researcher, Tel Aviv University · Sept 2026

• Big Techcs.AI

  Models learn when to reason, cutting tokens while improving accuracy

  Amazon.com · Sept 2026

• Chinese Techcs.CL

  Hierarchical supervision allocation improves long-horizon model distillation

  Ant Group, Alibaba International Digital Commerce Group · Sept 2026

• Chinese Techcs.AI

  Structuring noisy file environments improves agents’ performance on complex tasks

  Shanghai Jiao Tong University, Theseus Labs · Sept 2026

• Chinese Techcs.AI

  Adaptive feedback helps reinforcement-learning agents target their changing weaknesses

  ShanghaiTech University, Ant Group · Sept 2026

• Chinese Techcs.AI

  Restructuring agent environments improves performance on noisy, evolving tasks

  Shanghai Jiao Tong University, Theseus Labs · Sept 2026

• Big Techcs.CL

  Eight-stage post-training recipe improves an open 106-billion-parameter language model

  Amazon · Sept 2026

• Chinese Techcs.AI

  Evolving terminal environments keeps training tasks challenging as agents improve

  Hunyuan Team, Tencent · Sept 2026

• Big Techcs.LG

  MILO co-evolves agent harnesses and the strategies that discover them

  Georgia Institute of Technology, AWS AI Labs · Oct 2026

• Top Universitycs.ROcode

  One video world model transfers physical dynamics across robot bodies

  Princeton University · Aug 2026

• Independentcs.AI

  Five-level ladder maps reasoning models beyond direct human oversight

  Sept 2026