Cover Image

Internal Representations as Indicators of Hallucinations in Agent Tool Selection

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Healy, Kait, Srinivasan, Bharathi, Madathil, Visakh, Wu, Jing
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents
by: Liang, Yijuan, et al.
Published: (2026)

A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents
by: Srinivasan, Vasundra
Published: (2026)

Hallucination Detection with the Internal Layers of LLMs
by: Preiß, Martin
Published: (2025)

Semantic Tool Discovery for Large Language Models: A Vector-Based Approach to MCP Tool Selection
by: Mudunuri, Sarat, et al.
Published: (2026)

AutoTool: Efficient Tool Selection for Large Language Model Agents
by: Jia, Jingyi, et al.
Published: (2025)

Stateless Decision Memory for Enterprise AI Agents
by: Srinivasan, Vasundra
Published: (2026)

Sequence-Level Certainty Reduces Hallucination In Knowledge-Grounded Dialogue Generation
by: Wan, Yixin, et al.
Published: (2023)

ToolTweak: An Attack on Tool Selection in LLM-based Agents
by: Sneh, Jonathan, et al.
Published: (2025)

MICE for CATs: Model-Internal Confidence Estimation for Calibrating Agents with Tools
by: Subramani, Nishant, et al.
Published: (2025)

Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models
by: Su, Weihang, et al.
Published: (2024)

ToolBeHonest: A Multi-level Hallucination Diagnostic Benchmark for Tool-Augmented Large Language Models
by: Zhang, Yuxiang, et al.
Published: (2024)

LLM Safety From Within: Detecting Harmful Content with Internal Representations
by: Jiao, Difan, et al.
Published: (2026)

IRIS: Implicit Reward-Guided Internal Sifting for Mitigating Multimodal Hallucination
by: Li, Yuanshuai, et al.
Published: (2026)

Do We Really Need External Tools to Mitigate Hallucinations? SIRA: Shared-Prefix Internal Reconstruction of Attribution
by: Qin, Tian, et al.
Published: (2026)

ASA: Training-Free Representation Engineering for Tool-Calling Agents
by: Wang, Youjin, et al.
Published: (2026)

Spectral Guardrails for Agents in the Wild: Detecting Tool Use Hallucinations via Attention Topology
by: Noël, Valentin
Published: (2026)

Causal Probing for Internal Visual Representations in Multimodal Large Language Models
by: Deng, Zehao, et al.
Published: (2026)

On the Internal Representations of Graph Metanetworks
by: Yeom, Taesun, et al.
Published: (2025)

SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integration
by: Ding, Keyan, et al.
Published: (2025)

The Tool-Overuse Illusion: Why Does LLM Prefer External Tools over Internal Knowledge?
by: Zeng, Yirong, et al.
Published: (2026)

ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
by: Hu, Xuhao, et al.
Published: (2026)

Affinity and Diversity: A Unified Metric for Demonstration Selection via Internal Representations
by: Kato, Mariko, et al.
Published: (2025)

Modality-Native Routing in Agent-to-Agent Networks: A Multimodal A2A Protocol Extension
by: Srinivasan, Vasundra
Published: (2026)

DART: Semantic Recoverability for Structured Tool Agents
by: Yang, Ke, et al.
Published: (2026)

EvoTool: Self-Evolving Tool-Use Policy Optimization in LLM Agents via Blame-Aware Mutation and Diversity-Aware Selection
by: Yang, Shuo, et al.
Published: (2026)

Visualizing and Benchmarking LLM Factual Hallucination Tendencies via Internal State Analysis and Clustering
by: Mao, Nathan, et al.
Published: (2026)

Probing LLM Hallucination from Within: Perturbation-Driven Approach via Internal Knowledge
by: Lee, Seongmin, et al.
Published: (2024)

HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents
by: Jin, Chao, et al.
Published: (2026)

MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them
by: Zhang, Weichen, et al.
Published: (2025)

Analyzing and Internalizing Complex Policy Documents for LLM Agents
by: Liu, Jiateng, et al.
Published: (2025)

Latent Agents: A Post-Training Procedure for Internalized Multi-Agent Debate
by: Yi, John Seon Keun, et al.
Published: (2026)

LLM-based Agents Suffer from Hallucinations: A Survey of Taxonomy, Methods, and Directions
by: Lin, Xixun, et al.
Published: (2025)

OptArgus: A Multi-Agent System to Detect Hallucinations in LLM-based Optimization Modeling
by: Li, Zhong, et al.
Published: (2026)

Evo-MARL: Co-Evolutionary Multi-Agent Reinforcement Learning for Internalized Safety
by: Pan, Zhenyu, et al.
Published: (2025)

CORVUS: Red-Teaming Hallucination Detectors via Internal Signal Camouflage in Large Language Models
by: Min, Nay Myat, et al.
Published: (2026)

Learning More from Less: Unlocking Internal Representations for Benchmark Compression
by: Zhang, Yueqi, et al.
Published: (2026)

Multimodal Policy Internalization for Conversational Agents
by: Wang, Zhenhailong, et al.
Published: (2025)

ToolRLA: Multiplicative Reward Decomposition for Tool-Integrated Agents
by: Liu, Pengbo
Published: (2026)

Hallucination as Exploit: Evidence-Carrying Multimodal Agents
by: Zhang, Guijia, et al.
Published: (2026)

Hallucination Detection and Hallucination Mitigation: An Investigation
by: Luo, Junliang, et al.
Published: (2024)