Evaluating Stochasticity in Deep Research Agents

Haotian Zhai, Elias Stengel-Eskin, Pratik Patil, Liu Leqi · Feb 26, 2026 · Citations: 0

Abstract

Deep Research Agents (DRAs) are promising agentic systems that gather and synthesize information to support research across domains such as financial decision-making, medical analysis, and scientific discovery. Despite recent improvements in research quality (e.g., outcome accuracy when ground truth is available), DRA system design often overlooks a critical barrier to real-world deployment: stochasticity. Under identical queries, repeated executions of DRAs can exhibit substantial variability in terms of research outcome, findings, and citations. In this paper, we formalize the study of stochasticity in DRAs by modeling them as information acquisition Markov Decision Processes. We introduce an evaluation framework that quantifies variance in the system and identify three sources of it: information acquisition, information compression, and inference. Through controlled experiments, we investigate how stochasticity from these modules across different decision steps influences the variance of DRA outputs. Our results show that reducing stochasticity can improve research output quality, with inference and early-stage stochasticity contributing the most to DRA output variance. Based on these findings, we propose strategies for mitigating stochasticity while maintaining output quality via structured output and ensemble-based query generation. Our experiments on DeepSearchQA show that our proposed mitigation methods reduce average stochasticity by 22% while maintaining high research quality.

HFEPX Relevance Assessment

This paper appears adjacent to HFEPX scope (human-feedback/eval), but does not show strong direct protocol evidence in metadata/abstract.

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

If you are doing eval pipeline work, start here:

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

Human Data Lens

Uses human feedback: No
Feedback types: None
Rater population: Unknown
Unit of annotation: Unknown
Expertise required: Medicine
Extraction source: Runtime deterministic fallback

Evaluation Lens

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

Protocol And Measurement Signals

Benchmarks / Datasets

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

Reported Metrics

accuracy

Research Brief

Deterministic synthesis

Generated Mar 2, 2026, 10:39 PM · Grounded in abstract + metadata only

Key Takeaways

Deep Research Agents (DRAs) are promising agentic systems that gather and synthesize information to support research across domains such as financial decision-making, medical…
We introduce an evaluation framework that quantifies variance in the system and identify three sources of it: information acquisition, information compression, and inference.

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).

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.

Recommended Queries

human-eval protocol design pairwise preference data quality inter-rater agreement adjudication

Research Summary

Contribution Summary

Deep Research Agents (DRAs) are promising agentic systems that gather and synthesize information to support research across domains such as financial decision-making, medical analysis, and scientific discovery.
We introduce an evaluation framework that quantifies variance in the system and identify three sources of it: information acquisition, information compression, and inference.
Based on these findings, we propose strategies for mitigating stochasticity while maintaining output quality via structured output and ensemble-based query generation.

Why It Matters For Eval

Deep Research Agents (DRAs) are promising agentic systems that gather and synthesize information to support research across domains such as financial decision-making, medical analysis, and scientific discovery.
We introduce an evaluation framework that quantifies variance in the system and identify three sources of it: information acquisition, information compression, and inference.

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

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.

DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science Category Neighbor

Citations: 0 Relevance: 3.30
- Shared arXiv category (cs.AI)
- Shared metric mentions
- Shared terminology (accuracy, evaluating)
Make It Hard to Hear, Easy to Learn: Long-Form Bengali ASR and Speaker Diarization via Extreme Augmentation and Perfect Alignment Category Neighbor

Citations: 0 Relevance: 3.30
- Shared arXiv category (cs.AI)
- Shared metric mentions
- Shared terminology (accuracy, research)
When Metrics Disagree: Automatic Similarity vs. LLM-as-a-Judge for Clinical Dialogue Evaluation Category Neighbor

Citations: 0 Relevance: 3.30
- Shared arXiv category (cs.AI)
- Shared metric mentions
- Shared terminology (accuracy, research)
AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning Category Neighbor

Citations: 0 Relevance: 2.85
- Shared arXiv category (cs.AI)
- Shared metric mentions
- Shared terminology (accuracy)
Confusion-Aware Rubric Optimization for LLM-based Automated Grading Category Neighbor

Citations: 0 Relevance: 2.85
- Shared arXiv category (cs.AI)
- Shared metric mentions
- Shared terminology (accuracy)
Quantity Convergence, Quality Divergence: Disentangling Fluency and Accuracy in L2 Mandarin Prosody Category Neighbor

Citations: 0 Relevance: 2.85
- Shared arXiv category (cs.AI)
- Shared metric mentions
- Shared terminology (accuracy)
Recycling Failures: Salvaging Exploration in RLVR via Fine-Grained Off-Policy Guidance Category Neighbor

Citations: 0 Relevance: 2.85
- Shared arXiv category (cs.AI)
- Shared metric mentions
- Shared terminology (accuracy)
Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning Category Neighbor

Citations: 0 Relevance: 2.85
- Shared arXiv category (cs.AI)
- Shared metric mentions
- Shared terminology (accuracy)

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

Post a Job Get a Quote