Deliberation Trace-Based Commitment Control for Multi-Agent Systems under Partial Observability
International Conference on Intelligent Computing and its Emerging Applications (ICEA 2026), Kaohsiung, Taiwan, Nov 19, 2026
Summary in three lines
- D-TRACE helps partially informed agents decide whether to gather more evidence, commit or fall back.
- A recurrent model uses the sequence of deliberation steps to estimate the value of another query.
- In matched cases with identical current features, the history-based model distinguished decision states that a snapshot model could not separate.
Abstract
Multi-agent systems under partial observability must integrate specialized-agent judgments while deciding whether to acquire more information or act. Fixed or uncertainty-based stopping criteria may not distinguish valuable deliberation from repetition after information value is exhausted. D-TRACE integrates planning, risk assessment, memory, reflection, and goal evaluation through a Shared Cognitive Workspace and hierarchical coordination while recording prior query outcomes, information gains, agent judgments, and candidate-action ranking changes. It continues QUERY only when the expected benefit of a query-induced action change exceeds query and query-count-dependent delay costs, then applies a risk constraint to select COMMIT or SAFE FALLBACK. Numerical analysis shows that the query boundary adapts to expected improvement, query cost, and prior query count rather than a fixed uncertainty threshold.
How to cite
H. Kang, W. Mao, and M. Tsukada, “Deliberation Trace-Based Commitment Control for Multi-Agent Systems under Partial Observability,” in International Conference on Intelligent Computing and its Emerging Applications (ICEA 2026), Kaohsiung, Taiwan, 2026.
BibTeX
@inproceedings{Kang2026,
title = {Deliberation Trace-Based Commitment Control for Multi-Agent Systems under Partial Observability},
author = {Hyeonbin Kang and Wencan Mao and Manabu Tsukada},
year = {2026},
date = {2026-11-19},
urldate = {2026-11-19},
booktitle = {International Conference on Intelligent Computing and its Emerging Applications (ICEA 2026)},
address = {Kaohsiung, Taiwan},
abstract = {Multi-agent systems under partial observability must integrate specialized-agent judgments while deciding whether to acquire more information or act. Fixed or uncertainty-based stopping criteria may not distinguish valuable deliberation from repetition after information value is exhausted. D-TRACE integrates planning, risk assessment, memory, reflection, and goal evaluation through a Shared Cognitive Workspace and hierarchical coordination while recording prior query outcomes, information gains, agent judgments, and candidate-action ranking changes. It continues QUERY only when the expected benefit of a query-induced action change exceeds query and query-count-dependent delay costs, then applies a risk constraint to select COMMIT or SAFE FALLBACK. Numerical analysis shows that the query boundary adapts to expected improvement, query cost, and prior query count rather than a fixed uncertainty threshold.},
keywords = {Other},
pubstate = {published},
tppubtype = {inproceedings}
}