Evolving and Executing Research Plans via Double-Loop Multi-Agent Collaboration
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908581070110720 |
|---|---|
| author | Zhang, Zhi Liu, Yan Hu, Zhejing Chen, Gong Zhong, Sheng-hua Cao, Jiannong |
| author_facet | Zhang, Zhi Liu, Yan Hu, Zhejing Chen, Gong Zhong, Sheng-hua Cao, Jiannong |
| contents | Automating the end-to-end scientific research process poses a fundamental challenge: it requires both evolving high-level plans that are novel and sound, and executing these plans correctly amidst dynamic and uncertain conditions. To address this bilevel challenge, we propose a novel Double-Loop Multi-Agent (DLMA) framework to solve the given research problem automatically. The leader loop, composed of professor agents, is responsible for evolving research plans. It employs an evolutionary algorithm through involvement, improvement, and integration meetings to iteratively generate and refine a pool of research proposals, exploring the solution space effectively. The follower loop, composed of doctoral student agents, is responsible for executing the best-evolved plan. It dynamically adjusts the plan during implementation via pre-hoc and post-hoc meetings, ensuring each step (e.g., drafting, coding) is well-supported by contextual and external observations. Extensive experiments on benchmarks like ACLAward and Laboratory show that DLMA generates research papers that achieve state-of-the-art scores in automated evaluation, significantly outperforming strong baselines. Ablation studies confirm the critical roles of both loops, with evolution driving novelty and execution ensuring soundness. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06761 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Evolving and Executing Research Plans via Double-Loop Multi-Agent Collaboration Zhang, Zhi Liu, Yan Hu, Zhejing Chen, Gong Zhong, Sheng-hua Cao, Jiannong Artificial Intelligence Computation and Language Automating the end-to-end scientific research process poses a fundamental challenge: it requires both evolving high-level plans that are novel and sound, and executing these plans correctly amidst dynamic and uncertain conditions. To address this bilevel challenge, we propose a novel Double-Loop Multi-Agent (DLMA) framework to solve the given research problem automatically. The leader loop, composed of professor agents, is responsible for evolving research plans. It employs an evolutionary algorithm through involvement, improvement, and integration meetings to iteratively generate and refine a pool of research proposals, exploring the solution space effectively. The follower loop, composed of doctoral student agents, is responsible for executing the best-evolved plan. It dynamically adjusts the plan during implementation via pre-hoc and post-hoc meetings, ensuring each step (e.g., drafting, coding) is well-supported by contextual and external observations. Extensive experiments on benchmarks like ACLAward and Laboratory show that DLMA generates research papers that achieve state-of-the-art scores in automated evaluation, significantly outperforming strong baselines. Ablation studies confirm the critical roles of both loops, with evolution driving novelty and execution ensuring soundness. |
| title | Evolving and Executing Research Plans via Double-Loop Multi-Agent Collaboration |
| topic | Artificial Intelligence Computation and Language |
| url | https://arxiv.org/abs/2510.06761 |