# SkillOpt-Lite: Better and Faster Agent Self-evolution via One Line of Vibe

arXiv: https://arxiv.org/abs/2607.03451 · HTML: https://mlsanity.com/paper/2607.03451/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Agent skill learning and evolution, one of 16 directions in LLM agents and tool use.
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 3 Jul 2026.

## Placed in

- LLM agents and tool use / [Agent skill learning and evolution](https://mlsanity.com/agents/agent-skill-learning-and-evolution/)

## Builds on (most cited first, 20 of 20)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Meta-Harness: End-to-End Optimization of Model Harnesses](https://mlsanity.com/paper/2603.28052/) (2026)
- [SearchQA: A New Q&A Dataset Augmented with Context from a Search Engine](https://mlsanity.com/paper/1704.05179/) (2017)
- [Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills](https://mlsanity.com/paper/2603.25158/) (2026)
- [A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning](https://mlsanity.com/paper/2006.06224/) (2020)
- [SkillOpt: Executive Strategy for Self-Evolving Agent Skills](https://mlsanity.com/paper/2605.23904/) (2026)
- [Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses](https://mlsanity.com/paper/2604.25850/) (2026)
- [SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation](https://mlsanity.com/paper/2406.14991/) (2024)
- [Self-Harness: Harnesses That Improve Themselves](https://mlsanity.com/paper/2606.09498/) (2026)
- [SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Support](https://mlsanity.com/paper/2604.08618/) (2026)
- [Code as Agent Harness](https://mlsanity.com/paper/2605.18747/) (2026)
- [OfficeQA Pro: An Enterprise Benchmark for End-to-End Grounded Reasoning](https://mlsanity.com/paper/2603.08655/) (2026)
- [LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence](https://mlsanity.com/paper/2605.25979/) (2026)
- [SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories](https://mlsanity.com/paper/2606.01311/) (2026)
- [SkillCAT: Contrastive, Assessment-Augmented and Topology-AwareSkill Self-Evolution for LLM Agents](https://mlsanity.com/paper/2606.13317/) (2026)
- [SoftSkill: Behavioral Compression for Contextual Adaptation](https://mlsanity.com/paper/2606.20333/) (2026)

## Built on by (most cited first, 20 of 20)

- [Mage-VL: An Efficient Codec-Native Streaming Multimodal Foundation Model](https://mlsanity.com/paper/2607.24904/) (2026)
- [Rethinking Self-Evolving Agent Skills: Feedback Dynamics over Multiple Rounds](https://mlsanity.com/paper/2608.02636/) (2026)
- [Rethinking Self-Evolving Agents: Do We Still Need Prescribed Optimization Pipelines?](https://mlsanity.com/paper/2608.09629/) (2026)
- [Agentic ESOpt: Fine-Tuning Long-Horizon LLM Agents with Minimal GPU Requirements](https://mlsanity.com/paper/2608.17310/) (2026)
- [Self-Evolving Code-with-Image Reasoning](https://mlsanity.com/paper/2608.11292/) (2026)
- [Rethinking Self-Evolution: A Constrained Exploration-Exploitation Process for Mitigating Skill Overfitting](https://mlsanity.com/paper/2607.26643/) (2026)
- [Experience Funnel: A State-Policy Alternating Loop for Self-Evolving Agents](https://mlsanity.com/paper/2609.08919/) (2026)
- [Certified Long-Horizon Code Agent Evolution via Validation-Gated Skill Optimization](https://mlsanity.com/paper/2609.32990/) (2026)
- [Skill Training with Corruption and Reconstruction Loop](https://mlsanity.com/paper/2607.27557/) (2026)
- [VeriSkill: A Self-Evolution Framework for Program Verification Skills](https://mlsanity.com/paper/2607.27733/) (2026)
- [Branch2Skill: Efficient Skill Evolution Through Reasoning Trees](https://mlsanity.com/paper/2608.08677/) (2026)
- [RedEvoAgent: Automatic Red-Teaming Agent with Experience-Driven Skill Evolution](https://mlsanity.com/paper/2608.27439/) (2026)
- [VideoResearcher: Self-Improving Tool Design for Long-Video Understanding](https://mlsanity.com/paper/2609.19664/) (2026)
- [SkillVine: Agent Skill Evolution via Branching Exploration](https://mlsanity.com/paper/2609.32731/) (2026)
- [SkillFocus: Evolving Agent Skills via Capability Decomposition](https://mlsanity.com/paper/2609.34397/) (2026)
- [Mara Chain: Rethinking Failure as a Stepping Stone for AI System Auto-Evolution](https://mlsanity.com/paper/2609.35855/) (2026)
- [SkillCome: Group Contrast Skill Optimization with Dual Memory](https://mlsanity.com/paper/2609.37128/) (2026)
- [SkillSpec: Consensus-Gated Agent Skill Evolution via Representation Specialization](https://mlsanity.com/paper/2610.00704/) (2026)
- [FreeEvolve: Learning to Evolve Beyond Fixed Loops](https://mlsanity.com/paper/2610.09197/) (2026)
- [Self-Evolving Agent Harness](https://mlsanity.com/paper/2610.18813/) (2026)

## Abstract (arXiv)

While skill optimization for autonomous agents has gained traction, existing methods rely on complex pipelines. This leaves a fundamental question unaddressed: What constitutes a minimal viable pipeline for skill optimization, where every component is justified by theory or empirical necessity? We formalize skill optimization via Zeroth-Order (ZO) optimization, mapping classical counterparts (central difference, trust regions) to recent literature. Noting that unlike blind numerical perturbations in classical ZO, skill trajectories serve as interpretable debugging feedback. Grounded in Claude Code philosophy and PAC learning, we establish three principles for convergence and generalization: file-system-based trajectory exploration, consensus attribute mining, and independent validation gating. Eliminating redundancies, we propose SkillOpt-Lite. It accelerates convergence and outperforms full SkillOpt: improving LiveMath by +8.8 points on GPT-5.5 and +25.4 points on GPT-5.4-nano, allowing the nano model to surpass standard GPT-5.4 optimized by SkillOpt. Finally, we integrate our framework into production coding agents like VSCode Copilot, enabling developers to evolve agent skills via one line of vibe. Because our framework treats all agent components simply as standard editable code, this minimal pipeline naturally generalizes to full harness optimization (HarnessOpt). On SpreadsheetBench, HarnessOpt enables GPT-5.4-nano to achieve 0.7758 accuracy, outperforming the larger GPT-5.5 running standard pipelines (0.7620). Code is available at https://github.com/EvolvingLMMs-Lab/SkillOpt-Lite.