arXiv cs.AI· Prithwish Jana, Nikos Kanakaris, Purak Jain, Anoop Deoras, Sahika Genc·· 4 小时前AI 评分38
Inventa:面向自主科学发现去中心化自改进智能体框架
Inventa: Decentralized Self-Improving Agents for Autonomous Scientific Discovery
AI 导读
Inventa 是一个面向自动化科学发现的去中心化自改进智能体框架,由自主研究单元与经过验证的共享知识构成,在覆盖检索、构思、提案写作与科学定律发现的五个基准上全部领先。其在 EurekaBench 上达到 73.6%,高于 CORAL 的 56.2%;在 IdeaBench 上每篇论文发现 26.0 个新想法,优于 ResearchAgent 的 18.6 个,且模型调用减少 82%。
正文 · 原文
Abstract:Large language model (LLM) agents can generate research ideas and improve scientific discovery through iterative experimentation. However, increasing the number of agents or iterations does not automatically translate to producing more diverse or feasible ideas. Agents may converge on similar candidates, propagate unsupported claims through shared memory components and repeatedly apply search strategies that no longer yield any improvements.
We introduce Inventa, a framework for automated scientific discovery that employs autonomous research units and verified shared knowledge. Each unit creates a lineage of candidate ideas using a mutator agent. A local orchestrator agent periodically adapts the mutator's harness. When progress stalls, the orchestrator agent replaces its model or restarts the idea evolution process. Verifiers evaluate each candidate idea and record verified improvements, useful components and constraint violations in a shared knowledge, the only channel between units. We evaluate Inventa on five benchmarks spanning the research cycle, covering retrieval (ScholarCatalyst), ideation (IdeaBench), proposal writing (IdeaScientist), and scientific law discovery (EurekaBench, SciLaws-Bench). It leads all five, achieving 73.6% on EurekaBench versus 56.2% for CORAL. On IdeaBench, it discovers 26.0 novel ideas per paper, compared with 18.6 for ResearchAgent, with 82% fewer model calls.
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.21847 [cs.LG] |
| (or arXiv:2611.21847v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2611.21847 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Nikos Kanakaris [view email]
[v1]
Mon, 16 Nov 2026 20:07:18 UTC (660 KB)
来源:arXiv cs.AI · arxiv.org