Alita-G: Self-Evolving Generative Agent for Agent Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908615030341632 |
|---|---|
| author | Qiu, Jiahao Qi, Xuan Wang, Hongru Juan, Xinzhe Wang, Yimin Zhao, Zelin Geng, Jiayi Guo, Jiacheng Li, Peihang Shi, Jingzhe Liu, Shilong Wang, Mengdi |
| author_facet | Qiu, Jiahao Qi, Xuan Wang, Hongru Juan, Xinzhe Wang, Yimin Zhao, Zelin Geng, Jiayi Guo, Jiacheng Li, Peihang Shi, Jingzhe Liu, Shilong Wang, Mengdi |
| contents | Large language models (LLMs) have been shown to perform better when scaffolded into agents with memory, tools, and feedback. Beyond this, self-evolving agents have emerged, but current work largely limits adaptation to prompt rewriting or failure retries. Therefore, we present ALITA-G, a self-evolution framework that transforms a general-purpose agent into a domain expert by systematically generating, abstracting, and curating Model Context Protocol (MCP) tools. In this framework, a generalist agent executes a curated suite of target-domain tasks and synthesizes candidate MCPs from successful trajectories. These are then abstracted to parameterized primitives and consolidated into an MCP Box. At inference time, ALITA-G performs retrieval-augmented MCP selection with the help of each tool's descriptions and use cases, before executing an agent equipped with the MCP Executor. Across several benchmarks GAIA, PathVQA, and Humanity's Last Exam, ALITA-G attains strong gains while reducing computation costs. On GAIA validation, it achieves 83.03% pass@1 and 89.09% pass@3, establishing a new state-of-the-art result while reducing mean tokens per example by approximately 15% relative to a strong baseline agent. ALITA-G thus provides a principled pathway from generalist capability to reusable, domain-specific competence, improving both accuracy and efficiency on complex reasoning tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_23601 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Alita-G: Self-Evolving Generative Agent for Agent Generation Qiu, Jiahao Qi, Xuan Wang, Hongru Juan, Xinzhe Wang, Yimin Zhao, Zelin Geng, Jiayi Guo, Jiacheng Li, Peihang Shi, Jingzhe Liu, Shilong Wang, Mengdi Artificial Intelligence Large language models (LLMs) have been shown to perform better when scaffolded into agents with memory, tools, and feedback. Beyond this, self-evolving agents have emerged, but current work largely limits adaptation to prompt rewriting or failure retries. Therefore, we present ALITA-G, a self-evolution framework that transforms a general-purpose agent into a domain expert by systematically generating, abstracting, and curating Model Context Protocol (MCP) tools. In this framework, a generalist agent executes a curated suite of target-domain tasks and synthesizes candidate MCPs from successful trajectories. These are then abstracted to parameterized primitives and consolidated into an MCP Box. At inference time, ALITA-G performs retrieval-augmented MCP selection with the help of each tool's descriptions and use cases, before executing an agent equipped with the MCP Executor. Across several benchmarks GAIA, PathVQA, and Humanity's Last Exam, ALITA-G attains strong gains while reducing computation costs. On GAIA validation, it achieves 83.03% pass@1 and 89.09% pass@3, establishing a new state-of-the-art result while reducing mean tokens per example by approximately 15% relative to a strong baseline agent. ALITA-G thus provides a principled pathway from generalist capability to reusable, domain-specific competence, improving both accuracy and efficiency on complex reasoning tasks. |
| title | Alita-G: Self-Evolving Generative Agent for Agent Generation |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2510.23601 |