PluginRSI: Recursive Improvement of Agent Harnesses with Reusable Plugins

arXiv:2609.32423 · cs.AI · Submitted 2026-09-26 · Read on arXiv

cs.AI

Submitted: 2026-09-26

Updated: 2026-09-26

Code: https://github.com/syr-cn/PluginRSI

Terminology

• Benchmark — 8× in this paper · explained in 2 episodes
• Reinforcement Learning — 7× in this paper · explained in 4 episodes
• Ablation — 6× in this paper · explained in 1 episode
• Adaptation — 5× in this paper · explained in 1 episode
• Agent Skills — 4× in this paper · explained in 1 episode
• Provenance — 4× in this paper · explained in 4 episodes
• Trace — 4× in this paper · explained in 2 episodes
• Accuracy — 3× in this paper · explained in 1 episode
• Agent Harness — 3× in this paper · explained in 2 episodes
• Agentic System — 3× in this paper · explained in 2 episodes
• Ablation study — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Agentic Harness Engineering — 2× in this paper
• Verification — 2× in this paper · explained in 2 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 4 episodes
• Darwin-Godel Machine — 1× in this paper
• Fine-Tuning — 1× in this paper · explained in 5 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Online Adaptation — 1× in this paper · explained in 3 episodes
• Reward Function — 1× in this paper · explained in 2 episodes
• Self-Evolving Agents — 1× in this paper · explained in 2 episodes
• Transferability — 1× in this paper · explained in 4 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
• The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
• MCP-Zero: Active Tool Discovery for Autonomous LLM Agents
• LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation
• Continual Harness: Online Adaptation for Self-Improving Foundation Agents
• Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses
• Position: Agentic Evolution is the Path to Evolving LLMs
• Adaptive Auto-Harness: Sustained Self-Improvement for Agentic System Deployment on Open-Ended Task Streams
• HarnessBank: Semantic Gene-Bank Search with Gated Verification for Agent-Harness Self-Evolution
• SkillClaw: Let Skills Evolve Collectively with Agentic Evolver
• FinanceQA: A Benchmark for Evaluating Financial Analysis Capabilities of Large Language Models
• Code as Agent Harness
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• Natural-Language Agent Harnesses
• Self-Improvements in Modern Agentic Systems: A Survey
• Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning
• Kimi K3: Open Frontier Intelligence
• FrontierScience: Evaluating AI's Ability to Perform Expert-Level Scientific Tasks
• Agentless: Demystifying LLM-based Software Engineering Agents

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection