{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T23:35:47Z","timestamp":1761176147052,"version":"build-2065373602"},"reference-count":0,"publisher":"IOS Press","isbn-type":[{"value":"9781643686318","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,21]],"date-time":"2025-10-21T00:00:00Z","timestamp":1761004800000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,21]]},"abstract":"<jats:p>Empowered by large language models (LLMs), intelligent agents have become a popular paradigm for interacting with open environments to facilitate AI deployment. However, hallucinations generated by LLMs\u2014where outputs are inconsistent with facts\u2014pose a significant challenge, undermining the credibility of intelligent agents. Only if hallucinations can be mitigated, the intelligent agents can be used in real-world without any catastrophic risk. Therefore, effective detection and mitigation of hallucinations are crucial to ensure the dependability of agents. Unfortunately, the related approaches either depend on white-box access to LLMs or fail to accurately identify hallucinations. To address the challenge posed by hallucinations of intelligent agents, we present HalMit, a novel black-box watchdog framework that models the generalization bound of LLM-empowered agents and thus detect hallucinations without requiring internal knowledge of the LLM\u2019s architecture. Specifically, a probabilistic fractal sampling technique is proposed to generate a sufficient number of queries to trigger the incredible responses in parallel, efficiently identifying the generalization bound of the target agent. Experimental evaluations demonstrate that HalMit significantly outperforms existing approaches in hallucination monitoring. Its black-box nature and superior performance make HalMit a promising solution for enhancing the dependability of LLM-powered systems.<\/jats:p>","DOI":"10.3233\/faia250910","type":"book-chapter","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:45:44Z","timestamp":1761126344000},"source":"Crossref","is-referenced-by-count":0,"title":["Towards Mitigation of Hallucination for LLM-Empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor"],"prefix":"10.3233","author":[{"given":"Siyuan","family":"Liu","sequence":"first","affiliation":[{"name":"College of Computer Science, Nankai University"},{"name":"Haihe Lab of ITAI"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjing","family":"Liu","sequence":"additional","affiliation":[{"name":"College of intelligent Science and Technology, Inner Mongolia University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhiwei","family":"Xu","sequence":"additional","affiliation":[{"name":"Haihe Lab of ITAI"},{"name":"Institute of Computing Technology, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Stony Brook University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Michigan Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Li","sequence":"additional","affiliation":[{"name":"College of Computer Science, Nankai University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"7437","container-title":["Frontiers in Artificial Intelligence and Applications","ECAI 2025"],"original-title":[],"link":[{"URL":"https:\/\/ebooks.iospress.nl\/pdf\/doi\/10.3233\/FAIA250910","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T09:45:45Z","timestamp":1761126345000},"score":1,"resource":{"primary":{"URL":"https:\/\/ebooks.iospress.nl\/doi\/10.3233\/FAIA250910"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,21]]},"ISBN":["9781643686318"],"references-count":0,"URL":"https:\/\/doi.org\/10.3233\/faia250910","relation":{},"ISSN":["0922-6389","1879-8314"],"issn-type":[{"value":"0922-6389","type":"print"},{"value":"1879-8314","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,21]]}}}