#Tool Use

85개의 포스트

[논문리뷰] SkillX: Automatically Constructing Skill Knowledge Bases for Agents

저자들은 에이전트의 경험을 계층적으로 구조화하여 재사용성을 극대화하는 SkillX 프레임워크를 제안합니다 . SkillX는 고성능 backbone 에이전트인 GLM-4.6을 사용하여 훈련 태스크를 수행하고, 성공한 trajectory로부터 Planning, Functional, Atomic 단계의 skill을 증류(distill)합니다.

#Review #LLM Agents #Skill Knowledge Base #Hierarchical Representation #Autonomous Experience Learning #Agent Self-Evolution #Tool Use

2026년 4월 6일

[논문리뷰] EVA: Efficient Reinforcement Learning for End-to-End Video Agent

Xuanyu Zheng이 arXiv에 게시한 'EVA: Efficient Reinforcement Learning for End-to-End Video Agent' 논문에 대한 자세한 리뷰입니다.

#Review #Video Agent #Reinforcement Learning #MLLM #Planning-before-Perception #Tool Use #KTO #GRPO

2026년 3월 25일

[논문리뷰] XSkill: Continual Learning from Experience and Skills in Multimodal Agents

Fung이 arXiv에 게시한 'XSkill: Continual Learning from Experience and Skills in Multimodal Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Agents #Continual Learning #Experience Learning #Skill Learning #Tool Use #Knowledge Base #Visual Reasoning

2026년 3월 12일

[논문리뷰] DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use

arXiv에 게시된 'DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic Task Synthesis #Diversity Scaling #Tool Use #Generalization #Reinforcement Learning #Supervised Fine-tuning

2026년 3월 12일

[논문리뷰] In-Context Reinforcement Learning for Tool Use in Large Language Models

arXiv에 게시된 'In-Context Reinforcement Learning for Tool Use in Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Large Language Models #Tool Use #In-Context Learning #Few-Shot Learning #SFT-free #Data Efficiency #Curriculum Learning

2026년 3월 11일

[논문리뷰] AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios

arXiv에 게시된 'AgentVista: Evaluating Multimodal Agents in Ultra-Challenging Realistic Visual Scenarios' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Agents #Visual Reasoning #Tool Use #Benchmark #Long-Horizon Tasks #Realistic Scenarios #Agentic Intelligence

2026년 3월 5일

[논문리뷰] Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory

Wei Wei이 arXiv에 게시한 'Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memory' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Long-Horizon Tasks #Memory Management #Indexed Experience Memory #Reinforcement Learning #Context Window #Tool Use #MEMEXRL

2026년 3월 4일

[논문리뷰] Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts

arXiv에 게시된 'Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts' 논문에 대한 자세한 리뷰입니다.

#Review #Small Language Model #Generalist AI #Reasoning #Code Generation #Agentic Behavior #Reinforcement Learning #Tool Use #Deep Search

2026년 2월 16일

[논문리뷰] BrowseComp-V^3: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents

Yanzhe Dan이 arXiv에 게시한 'BrowseComp-V^3: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLMs #Web Browsing Agents #Deep Search #Benchmark #Tool Use #Process Evaluation #Multimodal Reasoning #Open-world QA

2026년 2월 16일

[논문리뷰] LawThinker: A Deep Research Legal Agent in Dynamic Environments

arXiv에 게시된 'LawThinker: A Deep Research Legal Agent in Dynamic Environments' 논문에 대한 자세한 리뷰입니다.

#Review #Legal Reasoning #AI Agent #Large Language Models #Verification #Knowledge Management #Dynamic Environments #Procedural Compliance #Tool Use

2026년 2월 12일

[논문리뷰] Towards Autonomous Mathematics Research

arXiv에 게시된 'Towards Autonomous Mathematics Research' 논문에 대한 자세한 리뷰입니다.

#Review #Mathematics Research #Large Language Models #AI Agents #Theorem Proving #Tool Use #Gemini Deep Think #Autonomous Research #Human-AI Collaboration

2026년 2월 11일

[논문리뷰] LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth

arXiv에 게시된 'LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Language Agents #Long Context #Context Rot #Benchmarking #Context Management #Tool Use #Agent Evaluation #Dynamic Environments

2026년 2월 9일

[논문리뷰] AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration

Zhaoyang Yu이 arXiv에 게시한 'AOrchestra: Automating Sub-Agent Creation for Agentic Orchestration' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic Orchestration #Sub-Agent Creation #Language Agents #Dynamic Specialization #Context Management #Tool Use #Large Language Models #Cost-Performance Optimization

2026년 2월 3일

[논문리뷰] Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models

Zhen Fang이 arXiv에 게시한 'Vision-DeepResearch: Incentivizing DeepResearch Capability in Multimodal Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Large Language Models #Deep Research #Agentic AI #Tool Use #Visual Question Answering #Reinforcement Learning #Multi-scale Search

2026년 2월 2일

[논문리뷰] Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors

Bin Liang이 arXiv에 게시한 'Robust Tool Use via Fission-GRPO: Learning to Recover from Execution Errors' 논문에 대한 자세한 리뷰입니다.

#Review #Tool Use #Execution Errors #Error Recovery #Reinforcement Learning #LLMs #Agentic AI #GRPO #FISSION

2026년 2월 1일

[논문리뷰] ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas

Kaichi Yu이 arXiv에 게시한 'ASTRA: Automated Synthesis of agentic Trajectories and Reinforcement Arenas' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agent #Tool Use #Trajectory Synthesis #Reinforcement Learning #Environment Synthesis #Data Generation #Multi-turn Interaction #Automated Training

2026년 2월 1일

[논문리뷰] AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts

arXiv에 게시된 'AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts' 논문에 대한 자세한 리뷰입니다.

#Review #Long-Context LLMs #Autonomous Agents #Benchmark #Environment Rollouts #State Tracking #Tool Use #Memory Evaluation #Lateral Thinking Puzzles

2026년 1월 29일

[논문리뷰] AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security

arXiv에 게시된 'AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security' 논문에 대한 자세한 리뷰입니다.

#Review #AI Agents #Safety Guardrails #Explainable AI (XAI)#Risk Taxonomy #Benchmarking #LLM Safety #Tool Use #Agent Alignment

2026년 1월 27일

[논문리뷰] AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning

arXiv에 게시된 'AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLMs #Tool Orchestration #Visual Reasoning #Reinforcement Learning #Adaptive Learning #Generalization #Tool Use

2026년 1월 27일

[논문리뷰] DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints

arXiv에 게시된 'DeepPlanning: Benchmarking Long-Horizon Agentic Planning with Verifiable Constraints' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Long-Horizon Planning #Benchmarking #Verifiable Constraints #Tool Use #Constraint Optimization #Information Acquisition #Travel Planning #Shopping Planning

2026년 1월 26일

[논문리뷰] Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation

arXiv에 게시된 'Knowledge is Not Enough: Injecting RL Skills for Continual Adaptation' 논문에 대한 자세한 리뷰입니다.

#Review #LLMs #Continual Adaptation #Reinforcement Learning #Supervised Fine-Tuning #Skill Transfer #Task Arithmetic #Tool Use

2026년 1월 25일

[논문리뷰] LLM-in-Sandbox Elicits General Agentic Intelligence

arXiv에 게시된 'LLM-in-Sandbox Elicits General Agentic Intelligence' 논문에 대한 자세한 리뷰입니다.

#Review #LLM-in-Sandbox #Agentic Intelligence #Code Sandbox #Reinforcement Learning #Generalization #Tool Use #Multi-Modal Generation #Long-Context Processing

2026년 1월 22일

[논문리뷰] Agentic Reasoning for Large Language Models

arXiv에 게시된 'Agentic Reasoning for Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic Reasoning #LLM Agents #Self-Evolving AI #Multi-Agent Systems #Planning #Tool Use #Retrieval-Augmented Generation #Reinforcement Learning

2026년 1월 21일

[논문리뷰] User-Oriented Multi-Turn Dialogue Generation with Tool Use at scale

arXiv에 게시된 'User-Oriented Multi-Turn Dialogue Generation with Tool Use at scale' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-Turn Dialogue Generation #Tool Use #Autonomous Agents #Large Reasoning Models #User Simulation #Synthetic Data Generation #SQL-based Tools #Agentic Benchmarks

2026년 1월 13일

[논문리뷰] The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents

Junjue Wang이 arXiv에 게시한 'The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Calibration #Tool Use #Reinforcement Learning #Miscalibration #Overconfidence #Trustworthy AI

2026년 1월 13일

[논문리뷰] Lost in the Noise: How Reasoning Models Fail with Contextual Distractors

arXiv에 게시된 'Lost in the Noise: How Reasoning Models Fail with Contextual Distractors' 논문에 대한 자세한 리뷰입니다.

#Review #Robustness #Contextual Distractors #RAG #Reasoning Models #Alignment #Tool Use #NoisyBench #Rationale-Aware Reward #Inverse Scaling

2026년 1월 12일

[논문리뷰] Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization

arXiv에 게시된 'Thinking with Map: Reinforced Parallel Map-Augmented Agent for Geolocalization' 논문에 대한 자세한 리뷰입니다.

#Review #Geolocalization #LVLM #Map-Augmented Agent #Reinforcement Learning #Parallel Test-Time Scaling #Tool Use #MAPBench

2026년 1월 11일

[논문리뷰] Distilling Feedback into Memory-as-a-Tool

vicgalle이 arXiv에 게시한 'Distilling Feedback into Memory-as-a-Tool' 논문에 대한 자세한 리뷰입니다.

#Review #LLM #Continual Learning #Memory-Augmented Agents #Self-Correction #Feedback Distillation #Tool Use #Inference Cost Amortization #Rubric-based Learning

2026년 1월 11일

[논문리뷰] SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning

arXiv에 게시된 'SenseNova-MARS: Empowering Multimodal Agentic Reasoning and Search via Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Agents #Reinforcement Learning #Vision-Language Models #Tool Use #Agentic Reasoning #Image Search #HR-MMSearch #BN-GSPO

2026년 1월 4일

[논문리뷰] Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem

Wei Gao이 arXiv에 게시한 'Let It Flow: Agentic Crafting on Rock and Roll, Building the ROME Model within an Open Agentic Learning Ecosystem' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic Learning Ecosystem #Large Language Models #Reinforcement Learning #Agentic Crafting #Tool Use #ROME Model #Policy Optimization #Sandbox Environment

2025년 12월 31일

[논문리뷰] EcomBench: Towards Holistic Evaluation of Foundation Agents in E-commerce

arXiv에 게시된 'EcomBench: Towards Holistic Evaluation of Foundation Agents in E-commerce' 논문에 대한 자세한 리뷰입니다.

#Review #E-commerce #Foundation Agents #LLM Agents #Benchmark #Agent Evaluation #Tool Use #Multi-step Reasoning #Real-world Scenarios

2025년 12월 9일

[논문리뷰] ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning

arXiv에 게시된 'ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Reward Models #Agentic AI #Tool Use #Reinforcement Learning #Visual Reasoning #Multimodal LLMs #Instruction Following #Evaluation Benchmarks

2025년 12월 4일

[논문리뷰] DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models

arXiv에 게시된 'DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Sparse Attention #Reinforcement Learning #Agentic AI #Tool Use #Open-source LLM #DeepSeek

2025년 12월 2일

[논문리뷰] CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization

arXiv에 게시된 'CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language Models #Agentic Reasoning #Tool Use #Reinforcement Learning #Faithfulness Evaluation #Policy Optimization #Visual Search #Code Generation

2025년 12월 2일

[논문리뷰] PRInTS: Reward Modeling for Long-Horizon Information Seeking

Elias Stengel-Eskin이 arXiv에 게시한 'PRInTS: Reward Modeling for Long-Horizon Information Seeking' 논문에 대한 자세한 리뷰입니다.

#Review #Reward Modeling #Long-Horizon Tasks #Information Seeking #Large Language Models #Trajectory Summarization #Reinforcement Learning #Tool Use #Process Reward Models

2025년 11월 24일

[논문리뷰] M3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark

Bangwei Guo이 arXiv에 게시한 'M3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLM #Tool Use #Agent Benchmark #Model Context Protocol #Multi-Hop Reasoning #Multi-Threaded Execution #Evaluation Metrics #Similarity Alignment

2025년 11월 24일

[논문리뷰] DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

arXiv에 게시된 'DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Evolving Rubrics #Deep Research #LLM Agents #Tool Use #Long-form QA #Open-source AI #Dynamic Evaluation

2025년 11월 24일

[논문리뷰] Budget-Aware Tool-Use Enables Effective Agent Scaling

arXiv에 게시된 'Budget-Aware Tool-Use Enables Effective Agent Scaling' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Tool Use #Budget Awareness #Test-time Scaling #Cost-Performance #Web Search Agents #Planning #Self-Verification

2025년 11월 24일

[논문리뷰] GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization

arXiv에 게시된 'GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization' 논문에 대한 자세한 리뷰입니다.

#Review #Geolocalization #Agentic Models #Visual Reasoning #Web-Augmented #Multimodal LLMs #Reinforcement Learning #Tool Use #GeoBench

2025년 11월 23일

[논문리뷰] Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning

Yucong Luo이 arXiv에 게시한 'Agent-R1: Training Powerful LLM Agents with End-to-End Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Reinforcement Learning #Markov Decision Process #Tool Use #Multi-turn Interaction #Policy Optimization #Reward Shaping #Agent Framework

2025년 11월 18일

[논문리뷰] DeepEyesV2: Toward Agentic Multimodal Model

Guohai Xu이 arXiv에 게시한 'DeepEyesV2: Toward Agentic Multimodal Model' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic AI #Multimodal Models #Tool Use #Reinforcement Learning #Supervised Fine-tuning #Multimodal Reasoning #Web Search #Code Execution

2025년 11월 9일

[논문리뷰] CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents

Shijue Huang이 arXiv에 게시한 'CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Tool Use #Cost-Optimal Planning #Dynamic Environments #Benchmarking #Multi-Turn Interaction #Economic Reasoning

2025년 11월 9일

[논문리뷰] TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning

Shaoheng Lin이 arXiv에 게시한 'TIR-Bench: A Comprehensive Benchmark for Agentic Thinking-with-Images Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLMs #Agentic Reasoning #Thinking-with-Images #Visual Reasoning Benchmark #Tool Use #Image Manipulation #Fine-tuning

2025년 11월 9일

[논문리뷰] The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution

Haoze Wu이 arXiv에 게시한 'The Tool Decathlon: Benchmarking Language Agents for Diverse, Realistic, and Long-Horizon Task Execution' 논문에 대한 자세한 리뷰입니다.

#Review #Language Agents #Tool Use #Benchmarking #Long-Horizon Tasks #Realistic Environments #Multi-Application #Execution-Based Evaluation #Model Context Protocol (MCP)

2025년 10월 30일

[논문리뷰] SeeingEye: Agentic Information Flow Unlocks Multimodal Reasoning In Text-only LLMs

Jiaxuan You이 arXiv에 게시한 'SeeingEye: Agentic Information Flow Unlocks Multimodal Reasoning In Text-only LLMs' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Reasoning #Text-only LLM #Agentic AI #Information Flow #VQA #Structured Intermediate Representation #Decoupled Architecture #Tool Use

2025년 10월 30일

[논문리뷰] Tongyi DeepResearch Technical Report

arXiv에 게시된 'Tongyi DeepResearch Technical Report' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic LLM #Deep Research #Information Seeking #Reinforcement Learning #Synthetic Data #Context Management #Tool Use #Open-source AI

2025년 10월 29일

[논문리뷰] ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking

arXiv에 게시된 'ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic AI #Parallel Thinking #Information Seeking #LLM Agents #Context Window Optimization #Exploration Efficiency #Reasoning Aggregation #Tool Use

2025년 10월 29일

[논문리뷰] FunReason-MT Technical Report: Overcoming the Complexity Barrier in Multi-Turn Function Calling

arXiv에 게시된 'FunReason-MT Technical Report: Overcoming the Complexity Barrier in Multi-Turn Function Calling' 논문에 대한 자세한 리뷰입니다.

#Review #Function Calling #Multi-Turn Interaction #Large Language Models (LLMs)#Data Synthesis #Agentic AI #Tool Use #Chain-of-Thought (CoT)#Reinforcement Learning

2025년 10월 29일

[논문리뷰] AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis

arXiv에 게시된 'AgentFrontier: Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Data Synthesis #Zone of Proximal Development (ZPD)#Complex Reasoning #Tool Use #Automated Benchmarking #Agentic AI #Rejection Sampling Fine-Tuning

2025년 10월 29일

[논문리뷰] DeepAgent: A General Reasoning Agent with Scalable Toolsets

Jiajie Jin이 arXiv에 게시한 'DeepAgent: A General Reasoning Agent with Scalable Toolsets' 논문에 대한 자세한 리뷰입니다.

#Review #Autonomous Agents #Large Language Models #Tool Use #Reinforcement Learning #Memory Management #Tool Retrieval #Agentic Reasoning

2025년 10월 27일

[논문리뷰] AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite

Bhavana Dalvi이 arXiv에 게시한 'AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite' 논문에 대한 자세한 리뷰입니다.

#Review #AI Agents #Benchmarking #Scientific Research #LLM Evaluation #Agentic AI #Tool Use #Reproducibility #Cost-Aware Evaluation

2025년 10월 27일

[논문리뷰] PokeeResearch: Effective Deep Research via Reinforcement Learning from AI Feedback and Robust Reasoning Scaffold

arXiv에 게시된 'PokeeResearch: Effective Deep Research via Reinforcement Learning from AI Feedback and Robust Reasoning Scaffold' 논문에 대한 자세한 리뷰입니다.

#Review #Deep Research Agent #Reinforcement Learning from AI Feedback #RLOO Algorithm #Large Language Models #Tool Use #Self-Correction #Reasoning Scaffold #Agent Alignment

2025년 10월 22일

[논문리뷰] Agentic Reinforcement Learning for Search is Unsafe

arXiv에 게시된 'Agentic Reinforcement Learning for Search is Unsafe' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic Reinforcement Learning #LLM Safety #Tool Use #Search Models #Jailbreaking #Instruction Tuning #Vulnerability

2025년 10월 21일

[논문리뷰] VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation

arXiv에 게시된 'VLA^2: Empowering Vision-Language-Action Models with an Agentic Framework for Unseen Concept Manipulation' 논문에 대한 자세한 리뷰입니다.

#Review #Vision-Language-Action Models #Agentic Framework #Unseen Concept Manipulation #Out-of-Distribution Generalization #Tool Use #Web Retrieval #Object Detection #LIBERO Simulation

2025년 10월 17일

[논문리뷰] DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search

arXiv에 게시된 'DeepMMSearch-R1: Empowering Multimodal LLMs in Multimodal Web Search' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal LLM #Web Search #Visual Question Answering #Reinforcement Learning #Image Cropping #Self-Correction #Tool Use

2025년 10월 15일

[논문리뷰] NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents

Baixuan Xu이 arXiv에 게시한 'NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Scientific Law Discovery #Benchmarking #Metaphysical Shifts #Interactive Environments #Exploration-Exploitation #Tool Use

2025년 10월 10일

[논문리뷰] AlphaApollo: Orchestrating Foundation Models and Professional Tools into a Self-Evolving System for Deep Agentic Reasoning

Zongze Li이 arXiv에 게시한 'AlphaApollo: Orchestrating Foundation Models and Professional Tools into a Self-Evolving System for Deep Agentic Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Foundation Models #Agentic Reasoning #Tool Use #Self-Evolving System #Retrieval-Augmented Generation #Computational Tools #Error Correction

2025년 10월 9일

[논문리뷰] In-the-Flow Agentic System Optimization for Effective Planning and Tool Use

arXiv에 게시된 'In-the-Flow Agentic System Optimization for Effective Planning and Tool Use' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic Systems #Large Language Models (LLMs)#Tool Use #Reinforcement Learning (RL)#On-policy Optimization #Flow-based Group Refined Policy Optimization (Flow-GRPO)#Multi-turn Reasoning

2025년 10월 8일

[논문리뷰] VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications

arXiv에 게시된 'VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Benchmarking #Interactive Tasks #Real-world Applications #Tool Use #Multi-turn Conversation #Task Complexity

2025년 10월 1일

[논문리뷰] MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use

arXiv에 게시된 'MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Use' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Model Context Protocol #Benchmark #Tool Use #CRUD Operations #Workflow Automation #Stress Testing #Evaluation

2025년 10월 1일

[논문리뷰] InfoAgent: Advancing Autonomous Information-Seeking Agents

arXiv에 게시된 'InfoAgent: Advancing Autonomous Information-Seeking Agents' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Information Seeking #Reinforcement Learning #Data Synthesis #Web Search Tools #Tool Use #Deep Research Agents

2025년 10월 1일

[논문리뷰] UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios

Zeyu Qin이 arXiv에 게시한 'UltraHorizon: Benchmarking Agent Capabilities in Ultra Long-Horizon Scenarios' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Long-Horizon Reasoning #Benchmarking #Partially Observable #Tool Use #Memory Management #Exploration

2025년 9월 29일

[논문리뷰] Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning

Gang Li이 arXiv에 게시한 'Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #LLM Agents #Exploration-Exploitation #Self-Imitation Learning #Intrinsic Rewards #Curriculum Learning #Policy Entropy #Tool Use

2025년 9월 29일

[논문리뷰] ARE: Scaling Up Agent Environments and Evaluations

Matteo Bettini이 arXiv에 게시한 'ARE: Scaling Up Agent Environments and Evaluations' 논문에 대한 자세한 리뷰입니다.

#Review #Agent Environments #Agent Evaluation #LLM Agents #Asynchronous Systems #Reinforcement Learning #Tool Use #Multi-agent Collaboration #Benchmark

2025년 9월 23일

[논문리뷰] FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning

Jiashuo Liu이 arXiv에 게시한 'FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning' 논문에 대한 자세한 리뷰입니다.

#Review #Financial LLMs #Agent Benchmarking #Open-domain Search #Financial Reasoning #Time-Sensitive Data #Multi-hop QA #Tool Use

2025년 9월 19일

[논문리뷰] Towards General Agentic Intelligence via Environment Scaling

Guangyu Li이 arXiv에 게시한 'Towards General Agentic Intelligence via Environment Scaling' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic AI #Environment Scaling #Function Calling #Tool Use #Large Language Models #Synthetic Data Generation #Supervised Fine-tuning

2025년 9월 17일

[논문리뷰] Scaling Agents via Continual Pre-training

Guangyu Li이 arXiv에 게시한 'Scaling Agents via Continual Pre-training' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic LLMs #Continual Pre-training #Deep Research Agents #Tool Use #Multi-step Reasoning #Data Synthesis #Scaling Laws

2025년 9월 17일

[논문리뷰] MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools

Xiaorui Wang이 arXiv에 게시한 'MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools' 논문에 대한 자세한 리뷰입니다.

#Review #Language Agents #Tool Use #Benchmarks #Model Context Protocol (MCP)#LLM Evaluation #Agentic AI #Real-World Performance

2025년 9월 15일

[논문리뷰] Reinforcement Learning Foundations for Deep Research Systems: A Survey

Wei Han이 arXiv에 게시한 'Reinforcement Learning Foundations for Deep Research Systems: A Survey' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #Deep Research Systems #Agentic AI #Tool Use #Hierarchical Agents #Reward Design #Multimodal AI #RL Frameworks

2025년 9월 9일

[논문리뷰] VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use

Zhiheng Lyu이 arXiv에 게시한 'VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic Reinforcement Learning #Tool Use #Large Language Models #Reinforcement Learning from Verifiable Rewards (RLVR)#Asynchronous Execution #Multi-modal AI #Framework

2025년 9월 3일

[논문리뷰] The Landscape of Agentic Reinforcement Learning for LLMs: A Survey

Hejia Geng이 arXiv에 게시한 'The Landscape of Agentic Reinforcement Learning for LLMs: A Survey' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic Reinforcement Learning #Large Language Models #LLM Agents #Sequential Decision Making #Policy Optimization #Tool Use #Dynamic Environments #Autonomous AI

2025년 9월 3일

[논문리뷰] How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench

Jayanth Srinivasa이 arXiv에 게시한 'How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on τ-bench' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Tool Use #Function Calling #Input Reformulation #Dynamic Environments #τ-bench #Context Engineering #Multi-Agent Framework

2025년 9월 2일

[논문리뷰] rStar2-Agent: Agentic Reasoning Technical Report

Weijiang Xu이 arXiv에 게시한 'rStar2-Agent: Agentic Reasoning Technical Report' 논문에 대한 자세한 리뷰입니다.

#Review #Agentic Reinforcement Learning #Math Reasoning #Code Interpreter #Tool Use #GRPO-RoC #LLM Training Efficiency #Self-Reflection

2025년 8월 29일

[논문리뷰] MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers

Shashank Biju이 arXiv에 게시한 'MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Tool Use #Benchmarking #Model Context Protocol (MCP)#Cross-Domain Orchestration #Fuzzy Instructions #Multi-Step Tasks #Real-World Scenarios

2025년 8월 29일

[논문리뷰] AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications

Liuyi Yao이 arXiv에 게시한 'AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Agentic Applications #ReAct Paradigm #Framework #Tool Use #Multi-Agent Systems #Developer Experience #Evaluation

2025년 8월 25일

[논문리뷰] LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries

huuuyeah이 arXiv에 게시한 'LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries' 논문에 대한 자세한 리뷰입니다.

#Review #AI Agents #Tool Use #Model Context Protocol (MCP)#Benchmarking #Large Language Models (LLMs)#Real-world Tasks #Evaluation #Error Analysis

2025년 8월 22일

[논문리뷰] MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers

Prathyusha Jwalapuram이 arXiv에 게시한 'MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models #Benchmarking #Model Context Protocol #Tool Use #Real-World Applications #Agent Evaluation #Long Context #Unknown Tools

2025년 8월 21일

[논문리뷰] FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction

tianlecai이 arXiv에 게시한 'FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction' 논문에 대한 자세한 리뷰입니다.

#Review #LLM Agents #Future Prediction #Live Benchmark #Dynamic Evaluation #Data Contamination #Tool Use #Web Search #Financial Forecasting #Misinformation

2025년 8월 21일

[논문리뷰] MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents

Jun Dong이 arXiv에 게시한 'MM-BrowseComp: A Comprehensive Benchmark for Multimodal Browsing Agents' 논문에 대한 자세한 리뷰입니다.

#Review #Multimodal Browsing #AI Agents #Benchmark #Vision-Language Models #Reasoning #Tool Use #Deep Search

2025년 8월 20일

[논문리뷰] AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving

Jinjie Gu이 arXiv에 게시한 'AWorld: Dynamic Multi-Agent System with Stable Maneuvering for Robust GAIA Problem Solving' 논문에 대한 자세한 리뷰입니다.

#Review #Multi-Agent System #Agent Stability #LLM #Tool Use #GAIA Benchmark #Robustness #Dynamic Supervision #Maneuvering

2025년 8월 14일

[논문리뷰] Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments

Xuesong Yao이 arXiv에 게시한 'Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments' 논문에 대한 자세한 리뷰입니다.

#Review #Large Language Models (LLMs)#Tool Use #Reinforcement Learning (RL)#Automated Environment Generation #Feedback-Driven Training #Reward Mechanism #Contextual Understanding

2025년 8월 13일

[논문리뷰] Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL

Chuyi He이 arXiv에 게시한 'Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL' 논문에 대한 자세한 리뷰입니다.

#Review #Reinforcement Learning #LLM Agents #Agentic Search #Asynchronous RL #Long-Horizon Planning #Tool Use #Data Synthesis

2025년 8월 13일

[논문리뷰] UserBench: An Interactive Gym Environment for User-Centric Agents

Jianguo Zhang이 arXiv에 게시한 'UserBench: An Interactive Gym Environment for User-Centric Agents' 논문에 대한 자세한 리뷰입니다.

#Review #User-Centric AI #LLM Evaluation #Interactive Agents #Gym Environment #Preference Elicitation #Multi-turn Dialogue #Tool Use

2025년 8월 12일

[논문리뷰] OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks

Hongxing Li이 arXiv에 게시한 'OmniEAR: Benchmarking Agent Reasoning in Embodied Tasks' 논문에 대한 자세한 리뷰입니다.

#Review #Embodied AI #Agent Reasoning #LLM #Benchmarking #Tool Use #Multi-Agent Systems #Physical Interaction #Constraint Reasoning

2025년 8월 12일

[논문리뷰] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

Xinhao Yi이 arXiv에 게시한 'A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems' 논문에 대한 자세한 리뷰입니다.

#Review #Self-Evolving AI Agents #Lifelong Learning #Foundation Models #Multi-Agent Systems #Agent Optimization #Prompt Engineering #Tool Use #AI Safety #Survey

2025년 8월 12일