Why Your Deep Research Agent Fails? On Hallucination Evaluation in Full Research Trajectory

• URL: http://arxiv.org/abs/2601.22984v1
• Date: Fri, 30 Jan 2026 13:49:09 GMT
• Title: Why Your Deep Research Agent Fails? On Hallucination Evaluation in Full Research Trajectory
• Abstract summary: Diagnosing the failure mechanisms of Deep Research Agents (DRAs) remains a critical challenge.<n>Existing benchmarks predominantly rely on end-to-end evaluation, obscuring critical intermediate hallucinations.<n>We introduce the PIES taxonomy to categorize hallucinations along functional components and error properties.
• Score: 7.41972830438376
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Diagnosing the failure mechanisms of Deep Research Agents (DRAs) remains a critical challenge. Existing benchmarks predominantly rely on end-to-end evaluation, obscuring critical intermediate hallucinations, such as flawed planning, that accumulate throughout the research trajectory. To bridge this gap, we propose a shift from outcome-based to process-aware evaluation by auditing the full research trajectory. We introduce the PIES Taxonomy to categorize hallucinations along functional components (Planning vs. Summarization) and error properties (Explicit vs. Implicit). We instantiate this taxonomy into a fine-grained evaluation framework that decomposes the trajectory to rigorously quantify these hallucinations. Leveraging this framework to isolate 100 distinctively hallucination-prone tasks including adversarial scenarios, we curate DeepHalluBench. Experiments on six state-of-theart DRAs reveal that no system achieves robust reliability. Furthermore, our diagnostic analysis traces the etiology of these failures to systemic deficits, specifically hallucination propagation and cognitive biases, providing foundational insights to guide future architectural optimization. Data and code are available at https://github.com/yuhao-zhan/DeepHalluBench.

Related papers

• Tracing the Cascade: A Topology-Aware Evaluation Framework for Scientific Agent Hallucinations [27.330265411994258]
  SCHEMA is an evidence-grounded, topology-aware evaluation framework for hallucinations in scientific agents.<n>We show that hallucinations concentrate at a small set of highly connected knowledge hubs.<n>Results indicate that for high-stakes scientific applications, terminal accuracy alone is an insufficient signal of agent reliability.
  arXiv  Detail & Related papers  (2026-08-01T15:19:10Z)
• Before the Action: Benchmarking LLMs on Prospective Hypothesis Discovery [95.44432473367836]
  Large language models (LLMs) excel at answering pre-specified questions, yet their ability to navigate the open-ended, pre-conclusion stage of discovery remains largely unmeasured.<n>We introduce Prospective Hypothesis Discovery (PHD), which asks models to autonomously construct grounded, discnative, and testable hypothesis spaces from inconclusive evidence.<n>We introduce HypoArena, comprising HypoData, a benchmark of 988 cases across six scientific and analytical domains, and HypoEval, an evaluation framework for open-ended hypothesis sets.
  arXiv  Detail & Related papers  (2026-07-17T08:56:43Z)
• Locate-then-Sparsify: Attribution Guided Sparse Strategy for Visual Hallucination Mitigation [68.41785694664011]
  We propose a plug-and-play framework called Locate-Then-Sparsify for Feature Steering (LTS-FS)<n>It controls the steering intensity according to the hallucination relevance of each layer.<n>Our framework effectively mitigates hallucination while preserving strong performance.
  arXiv  Detail & Related papers  (2026-03-17T09:16:50Z)
• Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models [62.932580559941414]
  Vision-Language Models (VLMs) frequently "hallucinate" - generate plausible yet factually incorrect statements.<n>We propose a new paradigm for diagnosing hallucinations, recasting them from static output errors into dynamic pathologies of a model's computational cognition.
  arXiv  Detail & Related papers  (2026-03-16T17:20:38Z)
• DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing [53.85037373860246]
  We introduce Deep Synth-Eval, a benchmark designed to objectively evaluate information consolidation capabilities.<n>We propose a fine-grained evaluation protocol using General Checklists (for factual coverage) and Constraint Checklists (for structural organization)<n>Our results demonstrate that agentic plan-and-write significantly outperform single-turn generation.
  arXiv  Detail & Related papers  (2026-01-07T03:07:52Z)
• SHALE: A Scalable Benchmark for Fine-grained Hallucination Evaluation in LVLMs [52.03164192840023]
  Large Vision-Language Models (LVLMs) still suffer from hallucinations, i.e., generating content inconsistent with input or established world knowledge.<n>We propose an automated data construction pipeline that produces scalable, controllable, and diverse evaluation data.<n>We construct SHALE, a benchmark designed to assess both faithfulness and factuality hallucinations.
  arXiv  Detail & Related papers  (2025-08-13T07:58:01Z)
• ICR Probe: Tracking Hidden State Dynamics for Reliable Hallucination Detection in LLMs [50.18087419133284]
  hallucination detection methods leveraging hidden states predominantly focus on static and isolated representations.<n>We introduce a novel metric, the ICR Score, which quantifies the contribution of modules to the hidden states' update.<n>We propose a hallucination detection method, the ICR Probe, which captures the cross-layer evolution of hidden states.
  arXiv  Detail & Related papers  (2025-07-22T11:44:26Z)
• Theoretical Foundations and Mitigation of Hallucination in Large Language Models [0.0]
  Hallucination in Large Language Models (LLMs) refers to the generation of content that is not faithful to the input or the real-world facts.<n>This paper provides a rigorous treatment of hallucination in LLMs, including formal definitions and theoretical analyses.
  arXiv  Detail & Related papers  (2025-07-20T15:22:34Z)
• HalluLens: LLM Hallucination Benchmark [49.170128733508335]
  Large language models (LLMs) often generate responses that deviate from user input or training data, a phenomenon known as "hallucination"<n>This paper introduces a comprehensive hallucination benchmark, incorporating both new extrinsic and existing intrinsic evaluation tasks.
  arXiv  Detail & Related papers  (2025-04-24T13:40:27Z)
• Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations [82.42811602081692]
  This paper introduces a subsequence association framework to systematically trace and understand hallucinations.<n>Key insight is hallucinations that arise when dominant hallucinatory associations outweigh faithful ones.<n>We propose a tracing algorithm that identifies causal subsequences by analyzing hallucination probabilities across randomized input contexts.
  arXiv  Detail & Related papers  (2025-04-17T06:34:45Z)
• HalluEntity: Benchmarking and Understanding Entity-Level Hallucination Detection [16.27352940098609]
  We propose a new data set, HalluEntity, which annotates hallucination at the entity level.<n>Based on the dataset, we evaluate uncertainty-based hallucination detection approaches across 17 modern LLMs.<n>Our experimental results show that uncertainty estimation approaches focusing on individual token probabilities tend to over-predict hallucinations.
  arXiv  Detail & Related papers  (2025-02-17T16:01:41Z)
• Hallucination Detection: A Probabilistic Framework Using Embeddings Distance Analysis [2.089191490381739]
  We introduce a mathematically sound methodology to reason about hallucination, and leverage it to build a tool to detect hallucinations.<n>To the best of our knowledge, we are the first to show that hallucinated content has structural differences with respect to correct content.<n>We leverage these structural differences to develop a tool to detect hallucinated responses, achieving an accuracy of 66% for a specific configuration of system parameters.
  arXiv  Detail & Related papers  (2025-02-10T09:44:13Z)
• Reefknot: A Comprehensive Benchmark for Relation Hallucination Evaluation, Analysis and Mitigation in Multimodal Large Language Models [13.48296910438554]
  We introduce Reefknot, a comprehensive benchmark targeting relation hallucinations, comprising over 20,000 real-world samples.<n>We provide a systematic definition of relation hallucinations, integrating perceptive and cognitive perspectives, and construct a relation-based corpus using the Visual Genome scene graph dataset.<n>We propose a novel confidence-based mitigation strategy, which reduces the hallucination rate by an average of 9.75% across three datasets, including Reefknot.
  arXiv  Detail & Related papers  (2024-08-18T10:07:02Z)
• HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data [102.56792377624927]
  hallucinations inherent in machine-generated data remain under-explored. We present a novel hallucination detection and elimination framework, HalluciDoctor, based on the cross-checking paradigm. Our method successfully mitigates 44.6% hallucinations relatively and maintains competitive performance compared to LLaVA.
  arXiv  Detail & Related papers  (2023-11-22T04:52:58Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.