Skip to content
← Back to explorer

Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People

Gabriel Grand, Valerio Pepe, Jacob Andreas, Joshua B. Tenenbaum · Oct 23, 2025 · Citations: 0

Automatic Metrics
Open arXiv Find Implementation RSS feed Shortlist (0)

Data freshness

Extraction: Fresh

Check recency before relying on this page for active eval decisions. Use stale pages as context and verify against current hub results.

Metadata refreshed

Mar 6, 2026, 6:00 PM

Recent

Extraction refreshed

Mar 14, 2026, 6:33 AM

Fresh

Extraction source

Persisted extraction

Confidence 0.35

Abstract

Many emerging applications of AI--from scientific discovery to medical diagnosis--require agents to seek information strategically: forming hypotheses, asking targeted questions, and making decisions under uncertainty. In high-stakes settings with limited resources, do language models (LMs) behave like rational agents? Drawing on insights from human cognition, we develop methods to evaluate and enhance agentic information-seeking. First, we introduce a decision-oriented dialogue task called Collaborative Battleship, in which a Captain must balance exploration (asking questions) and action (taking shots), while a Spotter must supply accurate, contextually-grounded answers. Compared to human players (N=42), we find that many LM agents struggle to ask informative questions, produce accurate answers, and identify high-utility actions. To address these gaps, we develop novel Monte Carlo inference strategies for LMs inspired by Bayesian Experimental Design (BED). For Spotter agents, our approach boosts accuracy by up to 14.7% absolute over LM-only baselines; for Captain agents, it raises expected information gain (EIG) by up to 0.227 bits (94.2% of the achievable noise ceiling). Combined, these components yield sharper targeting (+0.303-0.374 F1), and enable weaker LMs, such as Llama-4-Scout, to outperform both humans (8% -> 82% win rate) and frontier models (0% -> 67% win rate vs. GPT-5) at ~1% of GPT-5's cost. We replicate these findings on Guess Who?, where our methods significantly boost accuracy (+28.3-42.4 p.p.), demonstrating their general applicability for building information-seeking agents.

Low-signal caution for protocol decisions

Use this page for context, then validate protocol choices against stronger HFEPX references before implementation decisions.

  • Extraction flags indicate low-signal or possible false-positive protocol mapping.
  • Extraction confidence is 0.35 (below strong-reference threshold).
Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub

HFEPX Relevance Assessment

This paper is adjacent to HFEPX scope and is best used for background context, not as a primary protocol reference.

Best use

Background context only

Use if you need

A secondary eval reference to pair with stronger protocol papers.

Main weakness

Extraction flags indicate low-signal or possible false-positive protocol mapping.

Trust level

Low

Eval-Fit Score

0/100 • Low

Treat as adjacent context, not a core eval-method reference.

Human Feedback Signal

Not explicit in abstract metadata

Evaluation Signal

Detected

HFEPX Fit

Adjacent candidate

Extraction confidence: Low

If you are doing eval pipeline work, start here:

Human Eval Hub LLM-as-Judge Hub Pairwise Preference Hub Tool-Use Eval Hub

Field Provenance & Confidence

Each key protocol field shows extraction state, confidence band, and data source so you can decide whether to trust it directly or validate from full text.

Human Feedback Types

missing

None explicit

Confidence: Low Source: Persisted extraction missing

No explicit feedback protocol extracted.

Evidence snippet: Many emerging applications of AI--from scientific discovery to medical diagnosis--require agents to seek information strategically: forming hypotheses, asking targeted questions, and making decisions under uncertainty.

Evaluation Modes

partial

Automatic Metrics

Confidence: Low Source: Persisted extraction evidenced

Includes extracted eval setup.

Evidence snippet: Many emerging applications of AI--from scientific discovery to medical diagnosis--require agents to seek information strategically: forming hypotheses, asking targeted questions, and making decisions under uncertainty.

Quality Controls

missing

Not reported

Confidence: Low Source: Persisted extraction missing

No explicit QC controls found.

Evidence snippet: Many emerging applications of AI--from scientific discovery to medical diagnosis--require agents to seek information strategically: forming hypotheses, asking targeted questions, and making decisions under uncertainty.

Benchmarks / Datasets

missing

Not extracted

Confidence: Low Source: Persisted extraction missing

No benchmark anchors detected.

Evidence snippet: Many emerging applications of AI--from scientific discovery to medical diagnosis--require agents to seek information strategically: forming hypotheses, asking targeted questions, and making decisions under uncertainty.

Reported Metrics

partial

Accuracy, F1, Win rate, Cost

Confidence: Low Source: Persisted extraction evidenced

Useful for evaluation criteria comparison.

Evidence snippet: For Spotter agents, our approach boosts accuracy by up to 14.7% absolute over LM-only baselines; for Captain agents, it raises expected information gain (EIG) by up to 0.227 bits (94.2% of the achievable noise ceiling).

Rater Population

missing

Unknown

Confidence: Low Source: Persisted extraction missing

Rater source not explicitly reported.

Evidence snippet: Many emerging applications of AI--from scientific discovery to medical diagnosis--require agents to seek information strategically: forming hypotheses, asking targeted questions, and making decisions under uncertainty.

Human Data Lens

  • Uses human feedback: No
  • Feedback types: None
  • Rater population: Unknown
  • Unit of annotation: Unknown
  • Expertise required: Medicine
  • Extraction source: Persisted extraction

Evaluation Lens

  • Evaluation modes: Automatic Metrics
  • Agentic eval: None
  • Quality controls: Not reported
  • Confidence: 0.35
  • Flags: low_signal, possible_false_positive

Protocol And Measurement Signals

Benchmarks / Datasets

No benchmark or dataset names were extracted from the available abstract.

Reported Metrics

accuracyf1win ratecost

Research Brief

Deterministic synthesis

Drawing on insights from human cognition, we develop methods to evaluate and enhance agentic information-seeking. HFEPX signals include Automatic Metrics with confidence 0.35. Updated from current HFEPX corpus.

Generated Mar 14, 2026, 6:33 AM · Grounded in abstract + metadata only

Key Takeaways

  • Drawing on insights from human cognition, we develop methods to evaluate and enhance agentic information-seeking.
  • First, we introduce a decision-oriented dialogue task called Collaborative Battleship, in which a Captain must balance exploration (asking questions) and action (taking shots),…

Researcher Actions

  • Treat this as method context, then pivot to protocol-specific HFEPX hubs.
  • Identify benchmark choices from full text before operationalizing conclusions.
  • Validate metric comparability (accuracy, f1, win rate).

Caveats

  • Generated from title, abstract, and extracted metadata only; full-paper implementation details are not parsed.
  • Low-signal flag detected: protocol relevance may be indirect.

Research Summary

Contribution Summary

  • Drawing on insights from human cognition, we develop methods to evaluate and enhance agentic information-seeking.
  • First, we introduce a decision-oriented dialogue task called Collaborative Battleship, in which a Captain must balance exploration (asking questions) and action (taking shots), while a Spotter must supply accurate, contextually-grounded…
  • To address these gaps, we develop novel Monte Carlo inference strategies for LMs inspired by Bayesian Experimental Design (BED).

Why It Matters For Eval

  • Drawing on insights from human cognition, we develop methods to evaluate and enhance agentic information-seeking.
  • For Spotter agents, our approach boosts accuracy by up to 14.7% absolute over LM-only baselines; for Captain agents, it raises expected information gain (EIG) by up to 0.227 bits (94.2% of the achievable noise ceiling).

Researcher Checklist

  • Gap: Human feedback protocol is explicit

    No explicit human feedback protocol detected.

  • Pass: Evaluation mode is explicit

    Detected: Automatic Metrics

  • Gap: Quality control reporting appears

    No calibration/adjudication/IAA control explicitly detected.

  • Gap: Benchmark or dataset anchors are present

    No benchmark/dataset anchor extracted from abstract.

  • Pass: Metric reporting is present

    Detected: accuracy, f1, win rate, cost

Category-Adjacent Papers (Broader Context)

These papers are nearby in arXiv category and useful for broader context, but not necessarily protocol-matched to this paper.

Need human evaluators for your AI research? Scale annotation with expert AI Trainers.

Post a Job Get a Quote