# Self-Evolving Agents via Likelihood-Guided Tool-Space Optimization

arXiv: https://arxiv.org/abs/2609.34151 · HTML: https://mlsanity.com/paper/2609.34151/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 49 of its 59 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 30 of 49)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [Phi-4 Technical Report](https://mlsanity.com/paper/2412.08905/) (2024)
- [Data Shapley: Equitable Valuation of Data for Machine Learning](https://mlsanity.com/paper/1904.02868/) (2019)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Continual Test-Time Domain Adaptation](https://mlsanity.com/paper/2203.13591/) (2022)
- [Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models](https://mlsanity.com/paper/2510.04618/) (2025)
- [Large Language Models as Tool Makers](https://mlsanity.com/paper/2305.17126/) (2023)
- [Gemma 4 Technical Report](https://mlsanity.com/paper/2607.02770/) (2026)
- [A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence](https://mlsanity.com/paper/2507.21046/) (2025)
- [Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory](https://mlsanity.com/paper/2504.07952/) (2025)
- [SkillOpt: Executive Strategy for Self-Evolving Agent Skills](https://mlsanity.com/paper/2605.23904/) (2026)
- [The Shapley Taylor Interaction Index](https://mlsanity.com/paper/1902.05622/) (2019)
- [AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls](https://mlsanity.com/paper/2402.04253/) (2024)
- [ContextCite: Attributing Model Generation to Context](https://mlsanity.com/paper/2409.00729/) (2024)
- [AgentEvolver: Towards Efficient Self-Evolving Agent System](https://mlsanity.com/paper/2511.10395/) (2025)
- [GTA: A Benchmark for General Tool Agents](https://mlsanity.com/paper/2407.08713/) (2024)
- [TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasks](https://mlsanity.com/paper/2401.12869/) (2024)
- [OctoTools: An Agentic Framework with Extensible Tools for Complex Reasoning](https://mlsanity.com/paper/2502.11271/) (2025)
- [From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions](https://mlsanity.com/paper/2410.08197/) (2024)
- [ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval](https://mlsanity.com/paper/2403.06551/) (2024)

## Abstract (arXiv)

Self-evolving agents can continually improve their behavior, while tools define the executable action space through which they interact with the environment. However, exposing the full tool library to model introduces substantial irrelevant context and can impair tool-use decisions. We study tool-space self-evolution, where each recurring task type maintains a persistent tool space which is constructed from accumulated output experience. We identify three limitations of existing methods: (1) output-unaware selection: they rely primarily on tool descriptions or model priors rather than observed tool outputs; (2) statelessness across request: they select tools independently for each request without consolidating prior output experience into persistent task-specific state; (3) inference cost: they repeatedly search, rank, or reason over candidate tools for subsequent requests of the same task. We address these limitations through output-aware tool scoring, persistent task-specific tool spaces, amortized tool selection, and reusable configurations across models. We introduce LOTS (Likelihood-Only Tool Scoring), which evolves an agent's tool space from accumulated output experience while keeping model parameters fixed. After each request, LOTS holds the model's generated answer and estimates each tool's contribution by measuring how much the answer likelihood changes when its observed output is removed. These contributions are aggregated within each recurring task to rank tools and update its persistent space. Across three benchmarks, LOTS improves task performance while substantially reducing tool context. More importantly, sequential experiments demonstrate that task-specific spaces persist and continue to improve over time, while cross-model experiments show that learned configurations transfer across different models.