Imagen de Portada

Learning When Not to Act: Mitigating Tool Abuse in Agentic Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Chen, Liuji, Tang, Dianxing, Shi, Xing, Chen, Dingshuo, Liu, Qiang, Wu, Shu, Wang, Liang
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Graffe: Graph Representation Learning via Diffusion Probabilistic Models
por: Chen, Dingshuo, et al.
Publicado: (2025)

EX-FEVER: A Dataset for Multi-hop Explainable Fact Verification
por: Ma, Huanhuan, et al.
Publicado: (2023)

Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning
por: Xu, Siyuan, et al.
Publicado: (2026)

ToolBrain: A Flexible Reinforcement Learning Framework for Agentic Tools
por: Le, Quy Minh, et al.
Publicado: (2025)

VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use
por: Jiang, Dongfu, et al.
Publicado: (2025)

Tool-Augmented Policy Optimization: Synergizing Reasoning and Adaptive Tool Use with Reinforcement Learning
por: Wu, Wenxun, et al.
Publicado: (2025)

Select Me! When You Need a Tool: A Black-box Text Attack on Tool Selection
por: Chen, Liuji, et al.
Publicado: (2025)

Learning When to Act: Interval-Aware Reinforcement Learning with Predictive Temporal Structure
por: Di Gioia, Davide
Publicado: (2026)

Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learning
por: Singh, Joykirat, et al.
Publicado: (2025)

Gradient Coupling: The Hidden Barrier to Generalization in Agentic Reinforcement Learning
por: Liu, Jingyu, et al.
Publicado: (2025)

Tools as Continuous Flow for Evolving Agentic Reasoning
por: Huang, Tairan, et al.
Publicado: (2026)

Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models
por: Yan, Shilin, et al.
Publicado: (2026)

Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization
por: Chen, Dingshuo, et al.
Publicado: (2024)

Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning
por: Xu, Ran, et al.
Publicado: (2025)

Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
por: Zheng, Haizhong, et al.
Publicado: (2025)

Teaching RL Agents to Act Better: VLM as Action Advisor for Online Reinforcement Learning
por: Wu, Xiefeng, et al.
Publicado: (2025)

Scaling Agentic Reinforcement Learning for Tool-Integrated Reasoning in VLMs
por: Lu, Meng, et al.
Publicado: (2025)

CM2: Reinforcement Learning with Checklist Rewards for Multi-Turn and Multi-Step Agentic Tool Use
por: Zhang, Zhen, et al.
Publicado: (2026)

LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning
por: Wang, Jianing, et al.
Publicado: (2026)

6GAgentGym: Tool Use, Data Synthesis, and Agentic Learning for Network Management
por: Chen, Jiao, et al.
Publicado: (2026)

AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs
por: Zheng, Haizhong, et al.
Publicado: (2026)

Scheduling Your LLM Reinforcement Learning with Reasoning Trees
por: Wang, Hong, et al.
Publicado: (2025)

FactGuard: Agentic Video Misinformation Detection via Reinforcement Learning
por: Li, Zehao, et al.
Publicado: (2026)

Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning
por: Pan, Haolin, et al.
Publicado: (2025)

ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning
por: Wang, Xiaoxuan, et al.
Publicado: (2026)

MolAct: An Agentic RL Framework for Molecular Editing and Property Optimization
por: Yang, Zhuo, et al.
Publicado: (2025)

DeepTravel: An End-to-End Agentic Reinforcement Learning Framework for Autonomous Travel Planning Agents
por: Ning, Yansong, et al.
Publicado: (2025)

ProCeedRL: Process Critic with Exploratory Demonstration Reinforcement Learning for LLM Agentic Reasoning
por: Gao, Jingyue, et al.
Publicado: (2026)

When should I search more: Adaptive Complex Query Optimization with Reinforcement Learning
por: Wen, Wei, et al.
Publicado: (2026)

Doctor-R1: Mastering Clinical Inquiry with Experiential Agentic Reinforcement Learning
por: Lai, Yunghwei, et al.
Publicado: (2025)

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

ProAct: Agentic Lookahead in Interactive Environments
por: Yu, Yangbin, et al.
Publicado: (2026)

AgenTRIM: Tool Risk Mitigation for Agentic AI
por: Betser, Roy, et al.
Publicado: (2026)

Agentic Transformers Provably Learn to Search via Reinforcement Learning
por: Yang, Tong, et al.
Publicado: (2026)

TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use
por: He, Pengfei, et al.
Publicado: (2025)

When Agents Fail to Act: A Diagnostic Framework for Tool Invocation Reliability in Multi-Agent LLM Systems
por: Huang, Donghao, et al.
Publicado: (2026)

Route-Induced Density and Stability (RIDE): Controlled Intervention and Mechanism Analysis of Routing-Style Meta Prompts on LLM Internal States
por: Zhang, Dianxing, et al.
Publicado: (2026)

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

Speculative Sampling with Reinforcement Learning
por: Wang, Chenan, et al.
Publicado: (2026)

PiCA: Pivot-Based Credit Assignment for Search Agentic Reinforcement Learning
por: Liu, Dongyi, et al.
Publicado: (2026)