self-improvement
6 notes, newest first.
Learning Meta-Skills for Agent Harness Design in Test-Time AI4AI
The preprint studies a Builder model that learns to construct better execution environments for a frozen Target model. Its Meta-Skill encodes when support is needed and what resources to provide; the Builder learns…
Recursive self-improvement of AI research agents
The preprint presents AIDE^2, a system that proposes code changes to an AI research agent, benchmarks modified versions on AI R&D tasks, and keeps changes that perform best on hidden evaluations. An autonomous…
SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness
SoL-Pi applies recursive self-improvement at the harness layer across many environments. The abstract describes mechanisms for action execution, context compaction, observation handling, and delegated reading; on a…
STRETCH the Boundaries: A Unified Self-Taught Framework for Progressive LLM Evolution
STRETCH uses a dual-loop setup: a Scaffolder generates adaptive challenges near a model’s capability boundary, while a Learner improves solving trajectories with reinforcement learning. The abstract reports experiments…
ScienceBuddy: Recursive-in-Recursive Self-Improvement for Interactive Scientific Agents
ScienceBuddy is described as an interactive scientific-research workspace that converts researcher requests, feedback, and execution evidence into tasks and evaluation rubrics for continual learning. Its…
Who Grades the Grader? Co-Evolving Evaluation Metrics and Skills for Self-Improving LLM Agents
The paper presents a method for creating and improving self-evolving agent systems, which are capable of developing, modifying, and discarding their own skills. The authors claim that in many real-world applications, a…
