REVECA: Adaptive Planning and Trajectory-Based Validation in Cooperative Language Agents Using Information Relevance and Relative Proximity

Seungwon Seo, SeongRae Noh, Junhyeok Lee, Soobin Lim, Won Hee Lee, HyeongYeop Kang

AAAI 2025 pp. 23295-23303

doi:10.1609/AAAI.V39I22.34496 /aaai/2025/seo2025aaai-reveca/

Abstract

We address the challenge of multi-agent cooperation, where agents achieve a common goal by cooperating with decentralized agents under complex partial observations. Existing cooperative agent systems often struggle with efficiently processing continuously accumulating information, managing globally suboptimal planning due to lack of consideration of collaborators, and addressing false planning caused by environmental changes introduced by other collaborators. To overcome these challenges, we propose the RElevance, Proximity, and Validation-Enhanced Cooperative Language Agent (REVECA), a novel cognitive architecture powered by GPT-4o-mini. REVECA enables efficient memory management, optimal planning, and cost-effective prevention of false planning by leveraging Relevance Estimation, Adaptive Planning, and Trajectory-based Validation. Extensive experimental results demonstrate REVECA's superiority over existing methods across various benchmarks, while a user study reveals its potential for achieving trustworthy human-AI cooperation.

PDF AAAI Semantic Scholar

Cite

Text

Seo et al. "REVECA: Adaptive Planning and Trajectory-Based Validation in Cooperative Language Agents Using Information Relevance and Relative Proximity." AAAI Conference on Artificial Intelligence, 2025. doi:10.1609/AAAI.V39I22.34496

Markdown

[Seo et al. "REVECA: Adaptive Planning and Trajectory-Based Validation in Cooperative Language Agents Using Information Relevance and Relative Proximity." AAAI Conference on Artificial Intelligence, 2025.](https://mlanthology.org/aaai/2025/seo2025aaai-reveca/) doi:10.1609/AAAI.V39I22.34496

BibTeX

@inproceedings{seo2025aaai-reveca,
  title     = {{REVECA: Adaptive Planning and Trajectory-Based Validation in Cooperative Language Agents Using Information Relevance and Relative Proximity}},
  author    = {Seo, Seungwon and Noh, SeongRae and Lee, Junhyeok and Lim, Soobin and Lee, Won Hee and Kang, HyeongYeop},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2025},
  pages     = {23295-23303},
  doi       = {10.1609/AAAI.V39I22.34496},
  url       = {https://mlanthology.org/aaai/2025/seo2025aaai-reveca/}
}