arXiv:2607. 00972v1 Announce Type: new Abstract: Trustworthy deployment of Agentic Retrieval-Augmented Generation (RAG) systems requires mechanisms for estimating when multi-stage reasoning pipelines may fail.
By Louis Donaldson, Connor Walker, Koorosh Aslansefat, Yiannis Papadopoulos
The paper introduces RUPA, a trajectory‑level uncertainty quantification framework for large language model agents. RUPA models an agent’s execution as a directed graph of reasoning states, tool interactions, and environment feedback, then propagates uncertainty across this graph to capture long‑range dependencies. Experiments on benchmarks such as τ‑2, Terminal‑Bench‑2, and GAIA show that RUPA outperforms existing methods, enabling earlier failure detection and more reliable agent execution.
By Zhengzhao Ma. Boxi Cao, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun
arXiv:2608. 14707v1 Announce Type: new Abstract: As large language model (LLM)-based multi-agent systems become increasingly capable, coordinating agents under uncertainty becomes a fundamental challenge.
By John Knowlton, Aritra Guha, Risto Miikkulainen
arXiv:2607. 02186v1 Announce Type: new Abstract: Software development is a complex task that demands cooperation among agents with diverse roles.
By Temitayo Olamilekan Ogunsusi, Lijun Qian, Xishuang Dong
PropUQ-MAS is a framework for uncertainty quantification in large language model (LLM) multi‑agent systems that models the system as a communication‑structured graph. It estimates the reliability of each step by combining local uncertainty with uncertainty inherited from upstream messages, addressing the risk of error propagation in inter‑agent communication. Experiments show consistent improvements in UQ metrics, with average gains of +6.10% in AUROC and +47.58% in PRR.
By Yaokun Liu, Yifan Liu, Daniel Yue Zhang, Ruichen Yao, Zelin Li, Dong Wang
arXiv:2607. 17331v1 Announce Type: new Abstract: Enterprise Resource Planning (ERP) systems record transactions reliably but still delegate almost all operational decision-making to human specialists, because classical rule-based automation cannot reason about exceptions and monolithic AI assistants degrade when asked to coordinate across functional boundaries.
By Zhihao Liu, Tianyu Wang, Xi Vincent Wang, Lihui Wang