TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks
Paper
•
2412.14161
•
Published
•
51
Agents
-
-
Training Software Engineering Agents and Verifiers with SWE-Gym
Paper • 2412.21139 • Published • 24 -
OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis
Paper • 2412.19723 • Published • 87 -
AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation
Paper • 2408.00764 • Published • 1 -
More Agents Is All You Need
Paper • 2402.05120 • Published • 57 -
OS-Copilot: Towards Generalist Computer Agents with Self-Improvement
Paper • 2402.07456 • Published • 46 -
Generative Agents: Interactive Simulacra of Human Behavior
Paper • 2304.03442 • Published • 13 -
Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models
Paper • 2310.04406 • Published • 10 -
AgentCoder: Multi-Agent-based Code Generation with Iterative Testing and Optimisation
Paper • 2312.13010 • Published • 6 -
GAIA: a benchmark for General AI Assistants
Paper • 2311.12983 • Published • 237 -
LLM Agent Operating System
Paper • 2403.16971 • Published • 72 -
Octopus v2: On-device language model for super agent
Paper • 2404.01744 • Published • 58 -
AutoCrawler: A Progressive Understanding Web Agent for Web Crawler Generation
Paper • 2404.12753 • Published • 43 -
Scaling Instructable Agents Across Many Simulated Worlds
Paper • 2404.10179 • Published • 28 -
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Paper • 2404.07972 • Published • 50 -
WILBUR: Adaptive In-Context Learning for Robust and Accurate Web Agents
Paper • 2404.05902 • Published • 22 -
Ferret-UI: Grounded Mobile UI Understanding with Multimodal LLMs
Paper • 2404.05719 • Published • 83 -
AutoWebGLM: Bootstrap And Reinforce A Large Language Model-based Web Navigating Agent
Paper • 2404.03648 • Published • 29 -
Voyager: An Open-Ended Embodied Agent with Large Language Models
Paper • 2305.16291 • Published • 11 -
LASER: LLM Agent with State-Space Exploration for Web Navigation
Paper • 2309.08172 • Published • 13 -
The Rise and Potential of Large Language Model Based Agents: A Survey
Paper • 2309.07864 • Published • 7 -
Reflexion: Language Agents with Verbal Reinforcement Learning
Paper • 2303.11366 • Published • 5 -
LEGENT: Open Platform for Embodied Agents
Paper • 2404.18243 • Published • 22 -
Diffusion for World Modeling: Visual Details Matter in Atari
Paper • 2405.12399 • Published • 30 -
OpenVLA: An Open-Source Vision-Language-Action Model
Paper • 2406.09246 • Published • 41 -
SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks
Paper • 2305.17390 • Published • 3 -
MMAU: A Holistic Benchmark of Agent Capabilities Across Diverse Domains
Paper • 2407.18961 • Published • 40 -
AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents
Paper • 2407.18901 • Published • 35 -
Large Language Monkeys: Scaling Inference Compute with Repeated Sampling
Paper • 2407.21787 • Published • 13 -
OmniParser for Pure Vision Based GUI Agent
Paper • 2408.00203 • Published • 25 -
WebArena: A Realistic Web Environment for Building Autonomous Agents
Paper • 2307.13854 • Published • 25 -
Diffusion Augmented Agents: A Framework for Efficient Exploration and Transfer Learning
Paper • 2407.20798 • Published • 24 -
Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents
Paper • 2408.07060 • Published • 42 -
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
Paper • 2408.06292 • Published • 126 -
SWE-bench-java: A GitHub Issue Resolving Benchmark for Java
Paper • 2408.14354 • Published • 41 -
AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments
Paper • 2405.07960 • Published • 1 -
On the limits of agency in agent-based models
Paper • 2409.10568 • Published • 14 -
DSBench: How Far Are Data Science Agents to Becoming Data Science Experts?
Paper • 2409.07703 • Published • 67 -
HyperAgent: Generalist Software Engineering Agents to Solve Coding Tasks at Scale
Paper • 2409.16299 • Published • 12 -
The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use
Paper • 2411.10323 • Published • 34 -
Generative World Explorer
Paper • 2411.11844 • Published • 77 -
GUI Agents: A Survey
Paper • 2412.13501 • Published • 29 -
Large Action Models: From Inception to Implementation
Paper • 2412.10047 • Published • 36 -
A3: Android Agent Arena for Mobile GUI Agents
Paper • 2501.01149 • Published • 22 -
ResearchTown: Simulator of Human Research Community
Paper • 2412.17767 • Published • 14 -
PC Agent: While You Sleep, AI Works -- A Cognitive Journey into Digital World
Paper • 2412.17589 • Published • 14 -
Agent-SafetyBench: Evaluating the Safety of LLM Agents
Paper • 2412.14470 • Published • 13 -
GenEx: Generating an Explorable World
Paper • 2412.09624 • Published • 97 -
AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials
Paper • 2412.09605 • Published • 29 -
The BrowserGym Ecosystem for Web Agent Research
Paper • 2412.05467 • Published • 22 -
Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction
Paper • 2412.04454 • Published • 70 -
Code-as-Monitor: Constraint-aware Visual Programming for Reactive and Proactive Robotic Failure Detection
Paper • 2412.04455 • Published • 38 -
MALT: Improving Reasoning with Multi-Agent LLM Training
Paper • 2412.01928 • Published • 45 -
Mars-PO: Multi-Agent Reasoning System Preference Optimization
Paper • 2411.19039 • Published • 1 -
Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learning
Paper • 2410.22304 • Published • 18 -
MALMM: Multi-Agent Large Language Models for Zero-Shot Robotics Manipulation
Paper • 2411.17636 • Published • 2 -
Cooperative Strategic Planning Enhances Reasoning Capabilities in Large Language Models
Paper • 2410.20007 • Published • 1 -
Enhancing LLM Agents for Code Generation with Possibility and Pass-rate Prioritized Experience Replay
Paper • 2410.12236 • Published • 1 -
Large Language Model-Brained GUI Agents: A Survey
Paper • 2411.18279 • Published • 31 -
ShowUI: One Vision-Language-Action Model for GUI Visual Agent
Paper • 2411.17465 • Published • 89 -
Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents
Paper • 2411.06559 • Published • 16 -
DynaMem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation
Paper • 2411.04999 • Published • 18 -
Large Language Models Orchestrating Structured Reasoning Achieve Kaggle Grandmaster Level
Paper • 2411.03562 • Published • 68 -
Agent Laboratory: Using LLM Agents as Research Assistants
Paper • 2501.04227 • Published • 94 -
InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection
Paper • 2501.04575 • Published • 25 -
SDPO: Segment-Level Direct Preference Optimization for Social Agents
Paper • 2501.01821 • Published • 20 -
SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents
Paper • 2310.11667 • Published • 4 -
WebWalker: Benchmarking LLMs in Web Traversal
Paper • 2501.07572 • Published • 23 -
Multiagent Finetuning: Self Improvement with Diverse Reasoning Chains
Paper • 2501.05707 • Published • 20 -
SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution
Paper • 2501.05040 • Published • 15 -
FAST: Efficient Action Tokenization for Vision-Language-Action Models
Paper • 2501.09747 • Published • 27 -
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
Paper • 2406.11896 • Published • 20 -
From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning
Paper • 2411.03817 • Published • 1 -
PaSa: An LLM Agent for Comprehensive Academic Paper Search
Paper • 2501.10120 • Published • 52 -
UI-TARS: Pioneering Automated GUI Interaction with Native Agents
Paper • 2501.12326 • Published • 65 -
Agent-R: Training Language Model Agents to Reflect via Iterative Self-Training
Paper • 2501.11425 • Published • 108 -
Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks
Paper • 2501.11733 • Published • 28 -
Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environments
Paper • 2501.10893 • Published • 26 -
FilmAgent: A Multi-Agent Framework for End-to-End Film Automation in Virtual 3D Spaces
Paper • 2501.12909 • Published • 71 -
IntellAgent: A Multi-Agent Framework for Evaluating Conversational AI Systems
Paper • 2501.11067 • Published • 13 -
SRMT: Shared Memory for Multi-agent Lifelong Pathfinding
Paper • 2501.13200 • Published • 68 -
QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search
Paper • 2502.02584 • Published • 17 -
Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?
Paper • 2502.00674 • Published • 13 -
TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets
Paper • 2502.01506 • Published • 38 -
Large Language Model Guided Self-Debugging Code Generation
Paper • 2502.02928 • Published • 13 -
ScoreFlow: Mastering LLM Agent Workflows via Score-based Preference Optimization
Paper • 2502.04306 • Published • 20 -
Training Language Models for Social Deduction with Multi-Agent Reinforcement Learning
Paper • 2502.06060 • Published • 38 -
CODESIM: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging
Paper • 2502.05664 • Published • 24 -
Hephaestus: Improving Fundamental Agent Capabilities of Large Language Models through Continual Pre-Training
Paper • 2502.06589 • Published • 20 -
WorldGUI: Dynamic Testing for Comprehensive Desktop GUI Automation
Paper • 2502.08047 • Published • 28 -
EmbodiedBench: Comprehensive Benchmarking Multi-modal Large Language Models for Vision-Driven Embodied Agents
Paper • 2502.09560 • Published • 35 -
The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
Paper • 2502.08235 • Published • 58 -
MLGym: A New Framework and Benchmark for Advancing AI Research Agents
Paper • 2502.14499 • Published • 192 -
PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PC
Paper • 2502.14282 • Published • 29 -
Magma: A Foundation Model for Multimodal AI Agents
Paper • 2502.13130 • Published • 58 -
Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents
Paper • 2502.11357 • Published • 10 -
TheoremExplainAgent: Towards Multimodal Explanations for LLM Theorem Understanding
Paper • 2502.19400 • Published • 48 -
Towards an AI co-scientist
Paper • 2502.18864 • Published • 51 -
PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving
Paper • 2502.16111 • Published • 9 -
TAG: A Decentralized Framework for Multi-Agent Hierarchical Reinforcement Learning
Paper • 2502.15425 • Published • 9 -
Mobile-Agent-V: Learning Mobile Device Operation Through Video-Guided Multi-Agent Collaboration
Paper • 2502.17110 • Published • 13 -
WebGames: Challenging General-Purpose Web-Browsing AI Agents
Paper • 2502.18356 • Published • 14 -
VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model
Paper • 2502.18906 • Published • 12 -
Curie: Toward Rigorous and Automated Scientific Experimentation with AI Agents
Paper • 2502.16069 • Published • 20 -
Agentic Reward Modeling: Integrating Human Preferences with Verifiable Correctness Signals for Reliable Reward Systems
Paper • 2502.19328 • Published • 23 -
ATLaS: Agent Tuning via Learning Critical Steps
Paper • 2503.02197 • Published • 9 -
Gemini Robotics: Bringing AI into the Physical World
Paper • 2503.20020 • Published • 29 -
AppAgentX: Evolving GUI Agents as Proficient Smartphone Users
Paper • 2503.02268 • Published • 11 -
Unified Video Action Model
Paper • 2503.00200 • Published • 14 -
MPO: Boosting LLM Agents with Meta Plan Optimization
Paper • 2503.02682 • Published • 28 -
MultiAgentBench: Evaluating the Collaboration and Competition of LLM agents
Paper • 2503.01935 • Published • 29 -
World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning
Paper • 2503.10480 • Published • 55 -
Automated Movie Generation via Multi-Agent CoT Planning
Paper • 2503.07314 • Published • 44 -
AlphaDrive: Unleashing the Power of VLMs in Autonomous Driving via Reinforcement Learning and Reasoning
Paper • 2503.07608 • Published • 23 -
SafeArena: Evaluating the Safety of Autonomous Web Agents
Paper • 2503.04957 • Published • 21 -
GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training
Paper • 2503.08525 • Published • 17 -
Agent models: Internalizing Chain-of-Action Generation into Reasoning models
Paper • 2503.06580 • Published • 19 -
MedAgentsBench: Benchmarking Thinking Models and Agent Frameworks for Complex Medical Reasoning
Paper • 2503.07459 • Published • 16 -
LocAgent: Graph-Guided LLM Agents for Code Localization
Paper • 2503.09089 • Published • 13 -
AI-native Memory 2.0: Second Me
Paper • 2503.08102 • Published • 13 -
UI-R1: Enhancing Action Prediction of GUI Agents by Reinforcement Learning
Paper • 2503.21620 • Published • 62 -
Agents Play Thousands of 3D Video Games
Paper • 2503.13356 • Published • 9 -
SWE-smith: Scaling Data for Software Engineering Agents
Paper • 2504.21798 • Published • 11 -
Survey on Evaluation of LLM-based Agents
Paper • 2503.16416 • Published • 95 -
Why Do Multi-Agent LLM Systems Fail?
Paper • 2503.13657 • Published • 47 -
SPIN-Bench: How Well Do LLMs Plan Strategically and Reason Socially?
Paper • 2503.12349 • Published • 44 -
API Agents vs. GUI Agents: Divergence and Convergence
Paper • 2503.11069 • Published • 37 -
TxAgent: An AI Agent for Therapeutic Reasoning Across a Universe of Tools
Paper • 2503.10970 • Published • 18 -
VideoMind: A Chain-of-LoRA Agent for Long Video Reasoning
Paper • 2503.13444 • Published • 17 -
STEVE: AStep Verification Pipeline for Computer-use Agent Training
Paper • 2503.12532 • Published • 17 -
SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks
Paper • 2503.15478 • Published • 13 -
Measuring AI Ability to Complete Long Tasks
Paper • 2503.14499 • Published • 15 -
Free-form language-based robotic reasoning and grasping
Paper • 2503.13082 • Published • 11 -
Large Language Model Agent: A Survey on Methodology, Applications and Challenges
Paper • 2503.21460 • Published • 83 -
MAPS: A Multi-Agent Framework Based on Big Seven Personality and Socratic Guidance for Multimodal Scientific Problem Solving
Paper • 2503.16905 • Published • 54 -
Open Deep Search: Democratizing Search with Open-source Reasoning Agents
Paper • 2503.20201 • Published • 48 -
MARS: A Multi-Agent Framework Incorporating Socratic Guidance for Automated Prompt Optimization
Paper • 2503.16874 • Published • 44 -
RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints
Paper • 2503.16408 • Published • 41 -
AgentRxiv: Towards Collaborative Autonomous Research
Paper • 2503.18102 • Published • 25 -
Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks
Paper • 2503.21696 • Published • 23 -
Defeating Prompt Injections by Design
Paper • 2503.18813 • Published • 22 -
MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understanding
Paper • 2503.13964 • Published • 20 -
Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems
Paper • 2504.01990 • Published • 300 -
PaperBench: Evaluating AI's Ability to Replicate AI Research
Paper • 2504.01848 • Published • 36 -
CodeARC: Benchmarking Reasoning Capabilities of LLM Agents for Inductive Program Synthesis
Paper • 2503.23145 • Published • 35 -
RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy
Paper • 2503.24388 • Published • 30 -
Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents
Paper • 2504.00906 • Published • 26 -
Towards Trustworthy GUI Agents: A Survey
Paper • 2503.23434 • Published • 21 -
Interpreting Emergent Planning in Model-Free Reinforcement Learning
Paper • 2504.01871 • Published • 12 -
ActionStudio: A Lightweight Framework for Data and Training of Large Action Models
Paper • 2503.22673 • Published • 12 -
Scaling Laws in Scientific Discovery with AI and Robot Scientists
Paper • 2503.22444 • Published • 12 -
VerifiAgent: a Unified Verification Agent in Language Model Reasoning
Paper • 2504.00406 • Published • 8 -
MedAgent-Pro: Towards Multi-modal Evidence-based Medical Diagnosis via Reasoning Agentic Workflow
Paper • 2503.18968 • Published • 8 -
A Unified Agentic Framework for Evaluating Conditional Image Generation
Paper • 2504.07046 • Published • 30 -
Agentic Knowledgeable Self-awareness
Paper • 2504.03553 • Published • 27 -
MOSAIC: Modeling Social AI for Content Dissemination and Regulation in Multi-Agent Simulations
Paper • 2504.07830 • Published • 18 -
SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement
Paper • 2504.03561 • Published • 18 -
APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay
Paper • 2504.03601 • Published • 17 -
ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning
Paper • 2503.22738 • Published • 17 -
V-MAGE: A Game Evaluation Framework for Assessing Visual-Centric Capabilities in Multimodal Large Language Models
Paper • 2504.06148 • Published • 13 -
SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills
Paper • 2504.07079 • Published • 12 -
ReTool: Reinforcement Learning for Strategic Tool Use in LLMs
Paper • 2504.11536 • Published • 62 -
Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning
Paper • 2504.08672 • Published • 55 -
MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft
Paper • 2504.08388 • Published • 42 -
TextArena
Paper • 2504.11442 • Published • 29 -
AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
Paper • 2504.08942 • Published • 28 -
MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?
Paper • 2504.09702 • Published • 18 -
SocioVerse: A World Model for Social Simulation Powered by LLM Agents and A Pool of 10 Million Real-World Users
Paper • 2504.10157 • Published • 17 -
Breaking the Data Barrier -- Building GUI Agents Through Task Generalization
Paper • 2504.10127 • Published • 17 -
ReZero: Enhancing LLM search ability by trying one-more-time
Paper • 2504.11001 • Published • 15 -
The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
Paper • 2504.08066 • Published • 14 -
Exploring Expert Failures Improves LLM Agent Tuning
Paper • 2504.13145 • Published • 12 -
MetaSynth: Meta-Prompting-Driven Agentic Scaffolds for Diverse Synthetic Data Generation
Paper • 2504.12563 • Published • 4 -
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Paper • 2504.17192 • Published • 120 -
FlowReasoner: Reinforcing Query-Level Meta-Agents
Paper • 2504.15257 • Published • 47 -
ToolRL: Reward is All Tool Learning Needs
Paper • 2504.13958 • Published • 48 -
OTC: Optimal Tool Calls via Reinforcement Learning
Paper • 2504.14870 • Published • 35 -
X-Teaming: Multi-Turn Jailbreaks and Defenses with Adaptive Multi-Agents
Paper • 2504.13203 • Published • 34 -
BookWorld: From Novels to Interactive Agent Societies for Creative Story Generation
Paper • 2504.14538 • Published • 30 -
UFO2: The Desktop AgentOS
Paper • 2504.14603 • Published • 29 -
LLMs are Greedy Agents: Effects of RL Fine-tuning on Decision-Making Abilities
Paper • 2504.16078 • Published • 21 -
WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
Paper • 2504.15785 • Published • 20