The papers

Most central to this idea first, not most recent.

• Chinese Techcs.CL

  Query-side adapters recover full-context quality in KV cache reuse

  Eastern Institute of Technology, Ningbo, The Hong Kong Polytechnic University · Sept 2026

• Top Universitycs.AI

  Tailoring agent harnesses per task beats one-size-fits-all optimization

  Rutgers University, Red Hat AI Innovation · Oct 2026

• Chinese Techcs.AI

  Safety systems that learn from runtime experience protect LLM agents

  East China Normal University, Shanghai Innovation Institute · Sept 2026

• Chinese Techcs.LG

  StepLearn lets agents use new knowledge immediately while requiring validation before persistent reuse.

  Renmin University of China, Tencent · Sept 2026

• Independentcs.AI

  Personalizing agents through cross-session interaction data boosts task success

  Sept 2026

• Top Universitycs.AI

  Reusable harness components let agents adapt workflows to each task

  University of Illinois Urbana-Champaign, University of Michigan, Ann Arbor · Oct 2026

• Big Techcs.CL

  Hidden-state trajectories help diffusion language models escape wrong answers

  Rochester Institute of Technology, NVIDIA Corporation · Sept 2026

• Chinese Techcs.CVcode

  Token-aware latent refinement improves vision-language reasoning at inference time

  Qwen Business Unit of Alibaba, Nanjing University · Sept 2026

• Chinese Techcs.AI

  Adaptive mechanism selection improves LLM optimization across changing search states

  ByteDance, The University of Hong Kong · Sept 2026

• Independentcs.AI

  Self-designed evaluators enable safer retries for long-horizon agents

  Sept 2026

• Big Techcs.AI

  FOCUS Compresses Agent Histories While Preserving Future Decisions

  M365 Research, Microsoft · Sept 2026

• Independentcs.CL

  Agents Learn to Revise Their Harnesses on Unseen Tasks

  Sept 2026

• Research Labcs.AI

  A single corrupted observation can derail vision-language robot policies

  Science Tokyo, RIKEN · Sept 2026

• Top Universitycs.RO

  Robots Can Revise Visual Plans Instead of Starting Over

  Beihang University, Peking University · Sept 2026

• Top Universitycs.AI

  Successful agent migrations require calibration beyond interface compatibility alone

  PwC China AI Center, Tsinghua University · Sept 2026