Cover Image

Preemptive Detection and Correction of Misaligned Actions in LLM Agents

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Fang, Haishuo, Zhu, Xiaodan, Gurevych, Iryna
Format:	Preprint
Published:	2024
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

DARA: Decomposition-Alignment-Reasoning Autonomous Language Agent for Question Answering over Knowledge Graphs
by: Fang, Haishuo, et al.
Published: (2024)

SpaRC and SpaRP: Spatial Reasoning Characterization and Path Generation for Understanding Spatial Reasoning Capability of Large Language Models
by: Rizvi, Md Imbesat Hassan, et al.
Published: (2024)

SPARE: Single-Pass Annotation with Reference-Guided Evaluation for Automatic Process Supervision and Reward Modelling
by: Rizvi, Md Imbesat Hassan, et al.
Published: (2025)

MAGneT: Coordinated Multi-Agent Generation of Synthetic Multi-Turn Mental Health Counseling Sessions
by: Mandal, Aishik, et al.
Published: (2025)

SciCoQA: Quality Assurance for Scientific Paper--Code Alignment
by: Baumgärtner, Tim, et al.
Published: (2026)

IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators
by: Paul, Indraneil, et al.
Published: (2024)

Towards Privacy-aware Mental Health AI Models: Advances, Challenges, and Opportunities
by: Mandal, Aishik, et al.
Published: (2025)

Multimodal Large Language Models to Support Real-World Fact-Checking
by: Geng, Jiahui, et al.
Published: (2024)

Sensitivity, Performance, Robustness: Deconstructing the Effect of Sociodemographic Prompting
by: Beck, Tilman, et al.
Published: (2023)

PeerQA: A Scientific Question Answering Dataset from Peer Reviews
by: Baumgärtner, Tim, et al.
Published: (2025)

Factual Self-Awareness in Language Models: Representation, Robustness, and Scaling
by: Tamoyan, Hovhannes, et al.
Published: (2025)

The Good, the Bad and the Constructive: Automatically Measuring Peer Review's Utility for Authors
by: Sadallah, Abdelrahman, et al.
Published: (2025)

World-Model-Augmented Web Agents with Action Correction
by: Shen, Zhouzhou, et al.
Published: (2026)

DOCE: Finding the Sweet Spot for Execution-Based Code Generation
by: Li, Haau-Sing, et al.
Published: (2024)

From Leaky Thoughts to Private Reasoning: Controlling What LRMs Say to Themselves
by: Puerto, Haritz, et al.
Published: (2026)

Hypothesis-Driven Feature Manifold Analysis in LLMs via Supervised Multi-Dimensional Scaling
by: Tiblias, Federico, et al.
Published: (2025)

MathTutorBench: A Benchmark for Measuring Open-ended Pedagogical Capabilities of LLM Tutors
by: Macina, Jakub, et al.
Published: (2025)

Robust Utility-Preserving Text Anonymization Based on Large Language Models
by: Yang, Tianyu, et al.
Published: (2024)

Uncertainty-Aware Decoding with Minimum Bayes Risk
by: Daheim, Nico, et al.
Published: (2025)

CORE-T: COherent REtrieval of Tables for Text-to-SQL
by: Soliman, Hassan, et al.
Published: (2026)

A Comprehensive Review of Datasets for Clinical Mental Health AI Systems
by: Mandal, Aishik, et al.
Published: (2025)

Illusion or Algorithm? Investigating Memorization, Emergence, and Symbolic Processing in In-Context Learning
by: Niu, Jingcheng, et al.
Published: (2025)

Towards Automated Error Discovery: A Study in Conversational AI
by: Petrak, Dominic, et al.
Published: (2025)

A Survey of Confidence Estimation and Calibration in Large Language Models
by: Geng, Jiahui, et al.
Published: (2023)

Preemptive Detection and Steering of LLM Misalignment via Latent Reachability
by: Karnik, Sathwik, et al.
Published: (2025)

From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning
by: Dinucu-Jianu, David, et al.
Published: (2025)

Self-Correcting Text-to-Video Generation with Misalignment Detection and Localized Refinement
by: Lee, Daeun, et al.
Published: (2024)

Stepwise Verification and Remediation of Student Reasoning Errors with Large Language Model Tutors
by: Daheim, Nico, et al.
Published: (2024)

ObscuraCoder: Powering Efficient Code LM Pre-Training Via Obfuscation Grounding
by: Paul, Indraneil, et al.
Published: (2025)

Emergent Misalignment is Easy, Narrow Misalignment is Hard
by: Soligo, Anna, et al.
Published: (2026)

An Investigation into Value Misalignment in LLM-Generated Texts for Cultural Heritage
by: Bu, Fan, et al.
Published: (2025)

HGOT: Hierarchical Graph of Thoughts for Retrieval-Augmented In-Context Learning in Factuality Evaluation
by: Fang, Yihao, et al.
Published: (2024)

Executable Code Actions Elicit Better LLM Agents
by: Wang, Xingyao, et al.
Published: (2024)

Model Merging by Uncertainty-Based Gradient Matching
by: Daheim, Nico, et al.
Published: (2023)

Preemptive Answer "Attacks" on Chain-of-Thought Reasoning
by: Xu, Rongwu, et al.
Published: (2024)

GroundAct: Can LLM Agents Ground Actions in Environmental States?
by: Wang, Zixuan, et al.
Published: (2025)

RIRAG: Regulatory Information Retrieval and Answer Generation
by: Gokhan, Tuba, et al.
Published: (2024)

On the Structural Memory of LLM Agents
by: Zeng, Ruihong, et al.
Published: (2024)

Can LLMs Automate Fact-Checking Article Writing?
by: Sahnan, Dhruv, et al.
Published: (2025)

Chat-TS: Enhancing Multi-Modal Reasoning Over Time-Series and Natural Language Data
by: Quinlan, Paul, et al.
Published: (2025)