MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them

• URL: http://arxiv.org/abs/2507.21017v1
• Date: Mon, 28 Jul 2025 17:38:29 GMT
• Title: MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them
• Authors: Weichen Zhang, Yiyou Sun, Pohao Huang, Jiayue Pu, Heyue Lin, Dawn Song,
• Abstract summary: Hallucinations pose critical risks for large language model (LLM)-based agents.<n>We present MIRAGE-Bench, the first unified benchmark for eliciting and evaluating hallucinations in interactive environments.
• Score: 52.764019220214344
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Hallucinations pose critical risks for large language model (LLM)-based agents, often manifesting as hallucinative actions resulting from fabricated or misinterpreted information within the cognitive context. While recent studies have exposed such failures, existing evaluations remain fragmented and lack a principled testbed. In this paper, we present MIRAGE-Bench--Measuring Illusions in Risky AGEnt settings--the first unified benchmark for eliciting and evaluating hallucinations in interactive LLM-agent scenarios. We begin by introducing a three-part taxonomy to address agentic hallucinations: actions that are unfaithful to (i) task instructions, (ii) execution history, or (iii) environment observations. To analyze, we first elicit such failures by performing a systematic audit of existing agent benchmarks, then synthesize test cases using a snapshot strategy that isolates decision points in deterministic and reproducible manners. To evaluate hallucination behaviors, we adopt a fine-grained-level LLM-as-a-Judge paradigm with tailored risk-aware prompts, enabling scalable, high-fidelity assessment of agent actions without enumerating full action spaces. MIRAGE-Bench provides actionable insights on failure modes of LLM agents and lays the groundwork for principled progress in mitigating hallucinations in interactive environments.

Related papers

• Towards Mitigation of Hallucination for LLM-empowered Agents: Progressive Generalization Bound Exploration and Watchdog Monitor [18.9616029343245]
  hallucinations generated by large language models (LLMs) undermine the credibility of intelligent agents.<n>HalMit is a novel black-box watchdog framework that models the generalization bound of LLM-empowered agents.
  arXiv  Detail & Related papers  (2025-07-21T09:08:58Z)
• HEAL: An Empirical Study on Hallucinations in Embodied Agents Driven by Large Language Models [30.596530112268848]
  We present the first systematic study of hallucinations in large language models performing long-horizon tasks under scene-task inconsistencies.<n>Our goal is to understand to what extent hallucinations occur, what types of inconsistencies trigger them, and how current models respond.
  arXiv  Detail & Related papers  (2025-06-18T02:13:41Z)
• MIRAGE: Assessing Hallucination in Multimodal Reasoning Chains of MLLM [58.2298313720146]
  Multimodal hallucinations are multi-sourced and arise from diverse causes.<n>Existing benchmarks fail to adequately distinguish between perception-induced hallucinations and reasoning-induced hallucinations.
  arXiv  Detail & Related papers  (2025-05-30T05:54:36Z)
• 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)
• Analyzing LLM Behavior in Dialogue Summarization: Unveiling Circumstantial Hallucination Trends [38.86240794422485]
  We evaluate the faithfulness of large language models for dialogue summarization. Our evaluation reveals subtleties as to what constitutes a hallucination. We introduce two prompt-based approaches for fine-grained error detection that outperform existing metrics.
  arXiv  Detail & Related papers  (2024-06-05T17:49:47Z)
• INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection [39.52923659121416]
  We propose to explore the dense semantic information retained within textbfINternal textbfStates for halluctextbfInation textbfDEtection. A simple yet effective textbfEigenScore metric is proposed to better evaluate responses' self-consistency. A test time feature clipping approach is explored to truncate extreme activations in the internal states.
  arXiv  Detail & Related papers  (2024-02-06T06:23:12Z)
• A New Benchmark and Reverse Validation Method for Passage-level Hallucination Detection [63.56136319976554]
  Large Language Models (LLMs) generate hallucinations, which can cause significant damage when deployed for mission-critical tasks. We propose a self-check approach based on reverse validation to detect factual errors automatically in a zero-resource fashion. We empirically evaluate our method and existing zero-resource detection methods on two datasets.
  arXiv  Detail & Related papers  (2023-10-10T10:14:59Z)
• Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models [116.01843550398183]
  Large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks. LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge.
  arXiv  Detail & Related papers  (2023-09-03T16:56:48Z)
• Contrastive Learning Reduces Hallucination in Conversations [76.55116206021346]
  We propose a contrastive learning scheme, named MixCL. A novel mixed contrastive objective is proposed to explicitly optimize the implicit knowledge elicitation process of LMs. We show that MixCL achieves comparable performance to state-of-the-art KB-based approaches.
  arXiv  Detail & Related papers  (2022-12-20T16:26:18Z)

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.