…Harnesses That Improve Themselves (2026) EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning (2026) Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills (2026) From…
…Towards Test-time Prompt Learning in the Real World for Self-Improving Agents Published on Jun 9 Submitted by Shilong Liu on Jun 10 Princeton AI Lab Authors: , Shilong Liu , Abstract EEVEE…
…Verified Inference-Time Agent Skill Synthesis (2026) MIND-Skill: Quality-Guaranteed Skill Generation via Multi-Agent Induction and Deduction (2026) SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision (2026…
…Multi-Agent Data Generation for Accurate and Generalizable Function-Calling (2026) From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skills (2026) Pioneer Agent: Continual Improvement of Small…
Papers arxiv:2605.24202 When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs Published on May 22 Submitted by Yifan Zeng on Jun 2 Oregon State University…
…Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision (2026) Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents (2026) SkillX: Automatically Constructing Skill Knowledge Bases for Agents…
…converting in-the-wild guides into executable skills and continuously improving them from trajectories observable to the agent. To evaluate the capability of existing agents on this task, we introduce MMG2Skill-Bench…
…Generated by Qwen/Qwen2.5-Coder-32B-Instruct System prompt optimization improves agent behavior without modifying the underlying model, yielding human-readable, model-agnostic instructions. Existing methods build a prompt agent that…
…Data-Centric Autonomous AI Research (2026) Pioneer Agent: Continual Improvement of Small Language Models in Production (2026) Agent^2 RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training? (2026) ProfiliTable: Profiling…
…AI-generated summary Distributed blackbox consensus optimization is a fundamental problem in multi-agent systems, where agents must improve a global objective using only local objective queries and limited neighbor communication. Existing…
