Umeå University's logo

umu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
No future for LLM-based agents without formal dialogue verification
Umeå University, Faculty of Science and Technology, Department of Computing Science.ORCID iD: 0000-0003-4072-8795
Umeå University, Faculty of Science and Technology, Department of Computing Science.ORCID iD: 0000-0001-9379-4281
Umeå University, Faculty of Science and Technology, Department of Computing Science.ORCID iD: 0000-0002-6035-800x
2026 (English)In: AAMAS '26: Proceedings of the 25th international conference on autonomous agents and multiagent systems, Richland: The International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2026, p. 3921-3926Conference paper, Published paper (Refereed)
Abstract [en]

With the arrival of Large Language Models (LLMs), there is an explosion of agents characterised in terms of LLM-prompts. But LLMs lack consistency with their answers, and they are prone to hallucinations. This means that LLM-based agents are erratic agents. Hence, there are no guarantees that LLM-based agents will be aligned with an expected behaviour. We argue that formal dialogue verification is the way to go for minimising the potential negative side effects of erratic LLM-based agents. Erratic LLM-based agents are far from complying with basic Trustworthy AI principles such as technical robustness and safety. Formal Dialogue Verification methods provide rigorous mathematical frameworks for verifying fundamental behavioral properties of LLM-based agents.

Place, publisher, year, edition, pages
Richland: The International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS), 2026. p. 3921-3926
Keywords [en]
LLM-based agents, Trustworthy AI, Technical robustness and safety, Formal Dialogues, Formal Argumentation, Formal Verification
National Category
Computer Sciences
Research subject
Computer Science
Identifiers
URN: urn:nbn:se:umu:diva-256436DOI: 10.65109/JFKY8456Scopus ID: 2-s2.0-105041378900ISBN: 979-8-4007-2317-9 (electronic)OAI: oai:DiVA.org:umu-256436DiVA, id: diva2:2084025
Conference
25th International Conference on Autonomous Agents and Multiagent Systems (AAMAS 2026), Paphos, Cyprus, May 25-29, 2026
Available from: 2026-07-03 Created: 2026-07-03 Last updated: 2026-07-07Bibliographically approved

Open Access in DiVA

fulltext(976 kB)241 downloads
File information
File name FULLTEXT01.pdfFile size 976 kBChecksum SHA-512
f25dcc0945365d3b1eda3b6f68300a9eceebbcccf1a018892ee80ee456f85d88b51f71afee37dd5978777072448b21100f5d67a8e7ad879bd71789e7177136f5
Type fulltextMimetype application/pdf

Other links

Publisher's full textScopus

Authority records

Nieves, Juan CarlosBrännström, AndreasGuerrero Rosero, Esteban

Search in DiVA

By author/editor
Nieves, Juan CarlosBrännström, AndreasGuerrero Rosero, Esteban
By organisation
Department of Computing Science
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar
The number of downloads is the sum of all downloads of full texts. It may include eg previous versions that are now no longer available

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 1294 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf