paper-with-me

Papers

Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction

2025-10-16 · Xu Shen, Qi Zhang, Song Wang, Zhen Tan, Xinyu Zhao, Laura Yao, Vaishnav Tadiparthi, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Kwonjoon Lee, Tianlong Chen arxiv

Large Language Model based multi-agent systems (MAS) excel at collaborative problem solving but remain brittle to cascading errors: a single faulty step can propagate across agents and disrupt the trajectory. In this paper, we present MASC, a metacognitive framework that endows MAS with real-time, unsupervised, step-level error detection and self-correction. MASC rethinks detection as history-conditioned anomaly scoring via two complementary designs: (1) Next-Execution Reconstruction, which predicts the embedding of the next step from the query and interaction history to capture causal consistency, and (2) Prototype-Guided Enhancement, which learns a prototype prior over normal-step embeddings and uses it to stabilize reconstruction and anomaly scoring under sparse context (e.g., early steps). When an anomaly step is flagged, MASC triggers a correction agent to revise the acting agent's output before information flows downstream. On the Who&When benchmark, MASC consistently outperforms all baselines, improving step-level error detection by up to 8.47% AUC-ROC ; When plugged into diverse MAS frameworks, it delivers consistent end-to-end gains across architectures, confirming that our metacognitive monitoring and targeted correction can mitigate error propagation with minimal overhead.

📄 PDF Abstract BibTeX arXiv:2510.14319

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Truly Self-Improving Agents Require Intrinsic Metacognitive Learning

2025-06-05 · Tennison Liu, Mihaela van der Schaar

Self-improving agents aim to continuously acquire new capabilities with minimal supervision. However, current approaches face two key limitations: their self-improvement processes are often rigid, fail to generalize acro…

Stop Wandering: Efficient Vision-Language Navigation via Metacognitive Reasoning

2026-04-02 · Xueying Li, Feng Lyu, Hao Wu, Mingliu Liu 외 arxiv

Training-free Vision-Language Navigation (VLN) agents powered by foundation models can follow instructions and explore 3D environments. However, existing approaches rely on greedy frontier selection and passive spatial m…

Vision-Language Navigation

MetaCogAgent: A Metacognitive Multi-Agent LLM Framework with Self-Aware Task Delegation

2026-05-17 · Chenyu Wang, Yang Shu arxiv

Multi-agent large language model (LLM) systems have shown promise for solving complex tasks through agent collaboration. However, existing frameworks assign tasks based on predefined roles without considering whether an …

Metacognitive Behavioral Tuning of Large Language Models for Multi-Hop Question Answering

2026-02-26 · Ik-hwan Kim, Hyeongrok Han, Mingi Jung, Sangwon Yu 외 arxiv

Large Language Models (LLMs) often produce incorrect answers on multi-hop question answering even when the reasoning trace already contains a correct intermediate conclusion. We attribute this gap to weak self-regulation…

Multi-hop Question Answering

MetaMind: General and Cognitive World Models in Multi-Agent Systems by Meta-Theory of Mind

2026-02-28 · Lingyi Wang, Rashed Shelim, Walid Saad, Naren Ramakrishna arxiv

A major challenge for world models in multi-agent systems is to understand interdependent agent dynamics, predict interactive multi-agent trajectories, and plan over long horizons with collective awareness, without centr…