Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

ProMAS: Proactive Error Forecasting for Multi-Agent Systems Using Markov Transition Dynamics

About

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.

Xinkui Zhao, Sai Liu, Yifan Zhang, Qingyu Ma, Guanjie Cheng, Naibo Wang, Chang Liu• 2026

Related benchmarks

TaskDatasetResultRank
Failure attributionWho&When Algorithm-Generated
Step-level Accuracy24.75
13
Failure attributionWho&When Total
Step-level Accuracy22.97
13
Failure attributionWho&When Hand-Crafted
Step-level Accuracy19.14
13
Error ForecastingWho&When
Eta (%)26.79
6
Showing 4 of 4 rows

Other info

Follow for update