Agentic Reinforcement Learning for Search is Unsafe

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yang, Yushi, Padarha, Shreyansh, Lee, Andrew, Mahdi, Adam
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Enhancing Reasoning Capabilities in SLMs with Reward Guided Dataset Distillation
by: Padarha, Shreyansh
Published: (2025)

Party Ideologies and Political Polarization-Driven Conflicts: A Study of the Global South
by: Padarha, Shreyansh
Published: (2025)

Evaluating Fine-Tuning Efficiency of Human-Inspired Learning Strategies in Medical Question Answering
by: Yang, Yushi, et al.
Published: (2024)

How Does DPO Reduce Toxicity? A Mechanistic Neuron-Level Analysis
by: Yang, Yushi, et al.
Published: (2024)

Strategic Navigation or Stochastic Search? How Agents and Humans Reason Over Document Collections
by: Borchmann, Łukasz, et al.
Published: (2026)

Can sparse autoencoders be used to decompose and interpret steering vectors?
by: Mayne, Harry, et al.
Published: (2024)

Meta-Reinforcement Learning with Self-Reflection for Agentic Search
by: Xiao, Teng, et al.
Published: (2026)

Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learning
by: Mo, Fengran, et al.
Published: (2026)

Demystifying Reinforcement Learning in Agentic Reasoning
by: Yu, Zhaochen, et al.
Published: (2025)

Agentic-R: Learning to Retrieve for Agentic Search
by: Liu, Wenhan, et al.
Published: (2026)

Learning and Forgetting Unsafe Examples in Large Language Models
by: Zhao, Jiachen, et al.
Published: (2023)

CoSearch: Joint Training of Reasoning and Document Ranking via Reinforcement Learning for Agentic Search
by: Zeng, Hansi, et al.
Published: (2026)

Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning
by: Fan, Wei, et al.
Published: (2026)

SIRI: Scaling Iterative Reinforcement Learning with Interleaved Compression
by: Wen, Haoming, et al.
Published: (2025)

Agentic Reinforcement Learning with Implicit Step Rewards
by: Liu, Xiaoqian, et al.
Published: (2025)

GraphSearch: Agentic Search-Augmented Reasoning for Zero-Shot Graph Learning
by: Liu, Jiajin, et al.
Published: (2026)

RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models
by: Feng, Andrew Zhuoer, et al.
Published: (2026)

DeltaMem: Towards Agentic Memory Management via Reinforcement Learning
by: Zhang, Qi, et al.
Published: (2026)

LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations
by: Mayne, Harry, et al.
Published: (2025)

A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications
by: Lin, Minhua, et al.
Published: (2025)

The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
by: Zhang, Guibin, et al.
Published: (2025)

GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation
by: Yang, Cehao, et al.
Published: (2025)

AdaSearch: Balancing Parametric Knowledge and Search in Large Language Models via Reinforcement Learning
by: Lin, Tzu-Han, et al.
Published: (2025)

CARL: Criticality-Aware Agentic Reinforcement Learning
by: Shen, Leyang, et al.
Published: (2025)

Evaluating Defences against Unsafe Feedback in RLHF
by: Rosati, Domenic, et al.
Published: (2024)

SSRL: Self-Search Reinforcement Learning
by: Fan, Yuchen, et al.
Published: (2025)

DSPO: Stable and Efficient Policy Optimization for Agentic Search and Reasoning
by: Gu, Chenyang, et al.
Published: (2025)

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
by: Chen, Mingyang, et al.
Published: (2025)

AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning
by: Sun, Yuanfu, et al.
Published: (2026)

UnsafeChain: Enhancing Reasoning Model Safety via Hard Cases
by: Tomar, Raj Vardhan, et al.
Published: (2025)

LongWriter-Zero: Mastering Ultra-Long Text Generation via Reinforcement Learning
by: Wu, Yuhao, et al.
Published: (2025)

WideSearch: Benchmarking Agentic Broad Info-Seeking
by: Wong, Ryan, et al.
Published: (2025)

Improving In-Context Learning with Small Language Model Ensembles
by: Mojarradi, M. Mehdi, et al.
Published: (2024)

StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning
by: Wang, Daoyu, et al.
Published: (2026)

Clarify or Answer: Reinforcement Learning for Agentic VQA with Context Under-specification
by: Cao, Zongwan, et al.
Published: (2026)

From Correctness to Preference: A Framework for Personalized Agentic Reinforcement Learning
by: zhang, Ranxu, et al.
Published: (2026)

Self-Distilled Agentic Reinforcement Learning
by: Lu, Zhengxi, et al.
Published: (2026)

LRAS: Advanced Legal Reasoning with Agentic Search
by: Zhou, Yujin, et al.
Published: (2026)

OpenReward: Learning to Reward Long-form Agentic Tasks via Reinforcement Learning
by: Hu, Ziyou, et al.
Published: (2025)

Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning
by: Shen, Junhao, et al.
Published: (2026)