Explicit Trait Inference for Multi-Agent Coordination

Computer Science > Artificial Intelligence [Submitted on 21 Apr 2026] Explicit Trait Inference for Multi-Agent Coordination Suhaib Abdurahman, Etsuko Ishii, Katerina Margatina, Divya Bhargavi, Monica Sunkara, Yi Zhang LLM-based multi-agent systems (MAS) show promise on complex tasks but remain prone to coordination failures such as goal drift, error cascades, and misaligned behaviors. We propose Explicit Trait Inference (ETI), a psychologically grounded method for improving coordination. ETI enables agents to infer and track partner characteristics along two established psychological dimensions--warmth (e.g., trust) and competence (e.g., skill)--from interaction histories to guide decisions. We evaluate ETI in controlled settings (economic games), where it reduces payoff loss by 45-77%, and in more realistic, complex multi-agent settings (MultiAgentBench), where it improves performance by 3-29% depending on the scenario and model, relative to a CoT baseline. Additional analysis shows that gains are closely linked to trait inference: ETI profiles predict agents' actions, and informative profiles drive improvements. These results highlight ETI as a lightweight and robust mechanism for improving coordination in diverse multi-agent settings, and provide the first systematic evidence that LLM agents can (i) reliably infer others' traits from interaction histories and (ii) leverage structured awareness of others' traits for coordination. Subjects: Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) Cite as: arXiv:2604.19278 [cs.AI]   (or arXiv:2604.19278v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2604.19278 Focus to learn more Submission history From: Suhaib Abdurahman [view email] [v1] Tue, 21 Apr 2026 09:48:23 UTC (813 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-04 Change to browse by: cs cs.MA References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)