CORTEXA
← Browse
arxivcs.AIcs.MA2026-07-18

RELIC: Revealed Principles for Learning Interpretable Composable Skills in Multi-Agent Planning

Nguyen Viet Tuan Kiet, Bui Dinh Pham, Duong Quoc Chinh, Dao Van Tung, Tran Cong Dao, Huynh Thi Thanh Binh

Multi-agent planning becomes substantially harder when agents must improve specialized decision-making skills while keeping their internal implementations private. This regime arises when agents are developed independently, expose different interfaces and capabilities, and must nevertheless coordinate without sharing executable policies. Prior research has largely assumed centralized optimization, shared policy access, or common skill representations, making it poorly suited to privacy-constrained cooperation. We introduce RELIC, a framework for learning interpretable and composable skills via revealed principles. Each agent refines its own programmatic skill through private LLM-guided search, while a trusted orchestrator evaluates proposed updates solely through team-level performance. Successful behaviors are not broadcast as code; instead, they are abstracted into portable principles that other agents can instantiate within their own interfaces and recombine with local strategies. This separates coordination from implementation sharing, enabling cross-agent transfer under heterogeneous skill signatures. RELIC thus introduces a new paradigm for privacy-preserving skill learning and coordination in multi-agent planning.

View free PDFSource page

Related papers

arxivcs.MAcs.AI2026-07-31

SeekBrain: An Autonomous Multi-Agent System for Accelerating Neuroscience Discovery

Jiamin Wu, Peishan Xiang, Jingyang Chen, Yuqing Zhu, Yuxi Li, Ling Luo, et al.

Modern neuroscience relies on integrating multi-scale, multimodal datasets to uncover the neural principles underlying intelligence. However, analytical challenges posed by highly heterogeneous data and fragmented workflows increasingly constrain discoveries. Here we introduce Se…

View free PDFSource page
arxivcs.MAcs.AIecon.GN2026-07-23

pAI-Econ-claude: A Gated Human-in-the-Loop Multi-Agent Architecture for AI-Assisted Economic Theory Development

Chen Zhu, Xiaolu Wang, Weilong Zhang

In many social-science research tasks, such as economics, LLM-based agents must produce outputs for which no cheap, task-complete, machine-readable correctness signal exists. This creates a distinctive reliability problem for multi-agent systems: how should generation, critique,…

View free PDFSource page
arxivcs.LGcs.AIcs.MAcs.RO2026-07-23

Compact Latent Coordination for Autonomous Vehicles at Unsignalized Intersections

Gil Lifshits, Igal Bilik, Gilad Katz

Coordinating autonomous vehicles at unsignalized intersections remains a critical challenge for multi-agent reinforcement learning (MARL) systems, which typically struggle with combinatorial action spaces, reliance on privileged information, or rigid agent designs. We propose Mas…

View free PDFSource page
arxivcs.AIcs.MAcs.SE2026-07-31

Beyond Component Testing: Validating Agentic AI Systems

Fabio Orazio Mirto, Luca D'Agati, Giuseppe Tricomi, Stefano Silvestri, Francesco Longo, Antonio Puliafito, et al.

Agentic AI systems act through multi-step trajectories that combine planning, tool use, memory, interaction, and adaptation. This behavior stretches validation practice beyond component testing and one-shot input--output evaluation, because acceptable system behavior now depends…

View free PDFSource page
arxivcs.SEcs.AIcs.MA2026-07-30

Agentic Metaverse Services: A New As-a-Service Paradigm

Xiaofei Xu, Quan Z. Sheng, Zhongjie Wang, Boualem Benatallah, Xiao Wang, Ruipeng Han

Generative Artificial Intelligence (GenAI) is reconstructing the digital virtual world, upgrading agents through enhancing their abilities in autonomous learning, multi-modal interaction, content generation, and collaborative decision-making. In particular, the shift from convers…

View free PDFSource page