Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhao, Xinkui, Liu, Sai, Zhang, Yifan, Ma, Qingyu, Cheng, Guanjie, Wang, Naibo, Liu, Chang
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2603.20260
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866918400324796416
author Zhao, Xinkui
Liu, Sai
Zhang, Yifan
Ma, Qingyu
Cheng, Guanjie
Wang, Naibo
Liu, Chang
author_facet Zhao, Xinkui
Liu, Sai
Zhang, Yifan
Ma, Qingyu
Cheng, Guanjie
Wang, Naibo
Liu, Chang
contents The integration of Large Language Models into Multi-Agent Systems (MAS) has enabled the so-lution of complex, long-horizon tasks through collaborative reasoning. However, this collec-tive intelligence is inherently fragile, as a single logical fallacy can rapidly propagate and lead to system-wide failure. Most current research re-lies on post-hoc failure analysis, thereby hinder-ing real-time intervention. To address this, we propose PROMAS, a proactive framework utiliz-ing Markov transitions for predictive error anal-ysis. PROMAS extracts Causal Delta Features to capture semantic displacement, mapping them to a quantized Vector Markov Space to model reasoning as probabilistic transitions. By inte-grating a Proactive Prediction Head with Jump Detection, the method localizes errors via risk acceleration rather than static thresholds. On the Who&When benchmark, PROMAS achieves 22.97% step-level accuracy while processing only 27% of reasoning logs. This performance rivals reactive monitors like MASC while reducing data overhead by 73%. Although this strategy entails an accuracy trade-off compared to post-hoc meth-ods, it significantly improves intervention latency, balancing diagnostic precision with the real-time demands of autonomous reasoning.
format Preprint
id arxiv_https___arxiv_org_abs_2603_20260
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics
Zhao, Xinkui
Liu, Sai
Zhang, Yifan
Ma, Qingyu
Cheng, Guanjie
Wang, Naibo
Liu, Chang
Artificial Intelligence
The integration of Large Language Models into Multi-Agent Systems (MAS) has enabled the so-lution of complex, long-horizon tasks through collaborative reasoning. However, this collec-tive intelligence is inherently fragile, as a single logical fallacy can rapidly propagate and lead to system-wide failure. Most current research re-lies on post-hoc failure analysis, thereby hinder-ing real-time intervention. To address this, we propose PROMAS, a proactive framework utiliz-ing Markov transitions for predictive error anal-ysis. PROMAS extracts Causal Delta Features to capture semantic displacement, mapping them to a quantized Vector Markov Space to model reasoning as probabilistic transitions. By inte-grating a Proactive Prediction Head with Jump Detection, the method localizes errors via risk acceleration rather than static thresholds. On the Who&When benchmark, PROMAS achieves 22.97% step-level accuracy while processing only 27% of reasoning logs. This performance rivals reactive monitors like MASC while reducing data overhead by 73%. Although this strategy entails an accuracy trade-off compared to post-hoc meth-ods, it significantly improves intervention latency, balancing diagnostic precision with the real-time demands of autonomous reasoning.
title ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics
topic Artificial Intelligence
url https://arxiv.org/abs/2603.20260