Imagen de Portada

When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents?

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Li, Xinzhe, Tao, Yaguang
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

LiTS: A Modular Framework for LLM Tree Search
por: Li, Xinzhe, et al.
Publicado: (2026)

A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning
por: Li, Xinzhe
Publicado: (2024)

A Survey on LLM Test-Time Compute via Search: Tasks, LLM Profiling, Search Algorithms, and Relevant Frameworks
por: Li, Xinzhe
Publicado: (2025)

Chain-in-Tree: Back to Sequential Reasoning in LLM Tree Search
por: Li, Xinzhe
Publicado: (2025)

Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory
por: Li, Sijia, et al.
Publicado: (2025)

When Does Hierarchy Help? Benchmarking Agent Coordination in Event-Driven Industrial Scheduling
por: Wang, Ziqi, et al.
Publicado: (2026)

Are Tools All We Need? Unveiling the Tool-Use Tax in LLM Agents
por: Zhang, Kaituo, et al.
Publicado: (2026)

Learning to Rewrite Tool Descriptions for Reliable LLM-Agent Tool Use
por: Guo, Ruocheng, et al.
Publicado: (2026)

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

Guided by Trajectories: Repairing and Rewarding Tool-Use Trajectories for Tool-Integrated Reasoning
por: Gong, Siyu, et al.
Publicado: (2026)

Does More Inference-Time Compute Really Help Robustness?
por: Wu, Tong, et al.
Publicado: (2025)

Utility-Guided Agent Orchestration for Efficient LLM Tool Use
por: Liu, Boyan, et al.
Publicado: (2026)

Confidence-Gated Robot Autonomy: When Does Uncertainty Actually Help?
por: Gaus, Johannes A., et al.
Publicado: (2026)

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

FinToolBench: Evaluating LLM Agents for Real-World Financial Tool Use
por: Lu, Jiaxuan, et al.
Publicado: (2026)

Does Chain-of-Thought Reasoning Help Mobile GUI Agent? An Empirical Study
por: Zhang, Li, et al.
Publicado: (2025)

When Does Multi-Agent RL Improve LLM Workflows? Workflow, Scale, and Policy-Sharing Tradeoffs
por: Zeng, Yifan, et al.
Publicado: (2026)

MMedAgent: Learning to Use Medical Tools with Multi-modal Agent
por: Li, Binxu, et al.
Publicado: (2024)

Reducing Cognitive Overhead in Tool Use via Multi-Small-Agent Reinforcement Learning
por: Wang, Dayu, et al.
Publicado: (2025)

Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory
por: Yuen, Sizhe, et al.
Publicado: (2025)

When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use Agents
por: Zhou, Xiaolin, et al.
Publicado: (2026)

Enhanced Prediction of Multi-Agent Trajectories via Control Inference and State-Space Dynamics
por: Zhang, Yu, et al.
Publicado: (2024)

Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use
por: Thaman, Kunvar
Publicado: (2026)

MemCog: From Memory-as-Tool to Memory-as-Cognition in Conversational Agents
por: Li, Zihan, et al.
Publicado: (2026)

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

TUMIX: Multi-Agent Test-Time Scaling with Tool-Use Mixture
por: Chen, Yongchao, et al.
Publicado: (2025)

MIRIX: Multi-Agent Memory System for LLM-Based Agents
por: Wang, Yu, et al.
Publicado: (2025)

SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
por: Lin, Jiaye, et al.
Publicado: (2025)

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

DRC-Coder: Automated DRC Checker Code Generation Using LLM Autonomous Agent
por: Chang, Chen-Chia, et al.
Publicado: (2024)

Cost-Sensitive Neighborhood Aggregation for Heterophilous Graphs: When Does Per-Edge Routing Help?
por: Weiss, Eyal
Publicado: (2026)

When Does Language Transfer Help? Sequential Fine-Tuning for Cross-Lingual Euphemism Detection
por: Sammartino, Julia, et al.
Publicado: (2025)

Inference-Time Budget Control for LLM Search Agents
por: Fang, Zhengru, et al.
Publicado: (2026)

When Single-Agent with Skills Replace Multi-Agent Systems and When They Fail
por: Li, Xiaoxiao
Publicado: (2026)

When Continual Learning Moves to Memory: A Study of Experience Reuse in LLM Agents
por: Hu, Qisheng, et al.
Publicado: (2026)

When Skills Don't Help: A Negative Result on Procedural Knowledge for Tool-Grounded Agents in Offensive Cybersecurity
por: Chacko, Samuel Jacob, et al.
Publicado: (2026)

When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression
por: Zhang, Ruijie, et al.
Publicado: (2026)

E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memory
por: Wang, Kaixiang, et al.
Publicado: (2026)

Small LLMs Are Weak Tool Learners: A Multi-LLM Agent
por: Shen, Weizhou, et al.
Publicado: (2024)

CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents
por: Liu, Jiayu, et al.
Publicado: (2025)