The papers

Most central to this idea first, not most recent.

• Industrycs.CRcode

  Cyber agents hide critical weaknesses behind successful attack workflows

  National Research Council, University of Windsor · Sept 2026

• Industrycs.CL

  Serving stacks can distort local language-model tool-use evaluations

  Northeastern University, Seattle · Sept 2026

• Top Universitycs.AI

  Attribution-guided skill graphs improve targeted repairs for frozen language models

  National Key Laboratory for Novel Software Technology, Nanjing University · Sept 2026

• Chinese Techcs.AI

  Targeted reflection improves multi-agent systems by locating decisive errors

  Renmin University of China, Ant Group · Sept 2026

• Big Techcs.AI

  Structured behavioral abstractions improve diagnosis of failures in LLM agents

  Tsinghua University, Microsoft Research · Sept 2026

• Independentcs.AI

  Polished evidence makes LLM agents act on unknowable questions

  Aug 2026

• Research Labcs.SE

  Cross-task failure diagnosis makes LLM agent harness training faster

  Chengdu Institute of Computer Applications, Chinese Academy of Sciences, University of Chinese Academy of Sciences · Sept 2026

• Industrycs.AI

  Synthetic rewards train agents to diagnose simulated advertising anomalies

  Independent Researchers · Sept 2026

• Top Universitycs.AI

  Adaptive trace graphs improve failure attribution in multi-agent systems

  Tel Aviv University, AWS Agentic AI · Aug 2026

• Big Techcs.CL

  Process-based evaluation reveals where computer-use agents go wrong

  NVIDIA · Sept 2026

• Industrycs.CL

  Tool-call traces expose extraction failures that source fidelity misses

  Infineon Technologies AG · Sept 2026

• Big Techcs.AI

  Memory guidelines help language-model agents succeed consistently across repeated runs

  IBM Software Innovation Lab, IBM Research · Sept 2026

• Industrycs.AI

  Joint training helps small language models create and use tools

  Appier AI Research, National Taiwan University · Aug 2026

• Top Universitycs.RO

  Agent-side memory steers stateless robots through long manipulation tasks

  KU Leuven, Meituan Inc. · Sept 2026

• Independentcs.AIcode

  Good tool plans can still fail under resource constraints

  Aug 2026

• Big Techcs.CL

  Structural analysis filters noisy agent traces to pinpoint root causes

  University of Chinese Academy of Sciences, Microsoft Research · July 2026

• Big Techcs.AI

  Self-supervised method improves agent harnesses using past trajectories

  City University of Hong Kong, Microsoft Research Asia · June 2026

• Independentcs.AI

  Game-theoretic filtering helps agents suppress harmful memories during long tasks

  Sept 2026

• Big Techcs.AI

  Skill evolution improves agent performance in image generation workflows

  University of Pennsylvania, Nvidia · 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.AI

  Memory as state management instead of semantic retrieval improves long-horizon agents

  University of Science and Technology of China, Microsoft · June 2026

• Industrycs.SE

  Tracing and fault injection make multi-agent software workflows easier to inspect

  Delft University of Technology, JetBrains Research · Aug 2026