Skip to main content

# Information Seeking

2 related articles

Subscribe to updates

arXiv Oct 7, 2026
Eleven LLMs differ in which information they judge worth pursuing, producing markedly different breadth and depth in open-ended elicitation trajectories
Using 142 arguments from IBM-Rank-30k as a shared information space, the study feeds 11 open-weight instruction-tuned LLMs' judgments of whether a candidate piece of information is worth pursuing (the probability of an affirmative label, treated as an information-seeking score) into one sequential elicitation simulation with a fixed selection rule, fixed respondent behavior, and no natural-language question generation, characterizing how model-specific information-seeking preferences shape the breadth and depth of elicitation trajectories and testing the effects of interaction history, candidate-set size, response labels, and prompt wording.
Using 142 arguments from IBM-Rank-30k as a shared information space, the study feeds 11 open-weight instruction-tuned LLMs' judgments of whether a candidate piece of information is worth pursuing (the probability of an affirmative label, treated as an information-seeking score) into one sequential elicitation simulation with a fixed selection rule, fixed respondent behavior, and no natural-language question generation, characterizing how model-specific information-seeking preferences shape the breadth and depth of elicitation trajectories and testing the effects of interaction history, candidate-set size, response labels, and prompt wording.
Georgetown University
Victor De Lima（First author）
Information Elicitation Agent Elicitation Trajectory Simulation Information-Seeking Preference IBM-Rank-30k Large language models
arXiv Sep 30, 2026
ANTMAN replaces static partitioning with a revisable Need Graph: a 16x larger search space raises active coordination only 1.23x versus over 15x for partition-driven baselines
The work introduces ANTMAN, a multi-agent information-seeking framework that treats evolving unresolved information needs, rather than input partitions, as the unit of runtime coordination, maintaining a revisable Need Graph that tracks unresolved requirements, accumulated evidence, prior attempts, and search progress to control worker selection, routing, and task-local recovery; across multi-document QA, controlled long-context scaling, and structured navigation, ANTMAN increases active coordination by only 1.23x under a 16x increase in searchable context, compared with more than 15x for partition-driven baselines, while preserving strong answer quality and retaining most of its performance when execution is delegated to substantially smaller 8B worker models.
The work introduces ANTMAN, a multi-agent information-seeking framework that treats evolving unresolved information needs, rather than input partitions, as the unit of runtime coordination, maintaining a revisable Need Graph that tracks unresolved requirements, accumulated evidence, prior attempts, and search progress to control worker selection, routing, and task-local recovery; across multi-document QA, controlled long-context scaling, and structured navigation, ANTMAN increases active coordination by only 1.23x under a 16x increase in searchable context, compared with more than 15x for partition-driven baselines, while preserving strong answer quality and retaining most of its performance when execution is delegated to substantially smaller 8B worker models.
University of Illinois Urbana-Champaign
Jerry Wang（First author）
ANTMAN Need Graph Information Seeking Multi-Agent Collaboration

You’re all caught up