{"total":62,"rows":[{"id":"2509.25140","title":"ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory","created":"2025-09-29","cited_by_count":284,"area":"lr"},{"id":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223,"area":"lr"},{"id":"2504.00906","title":"Agent S2: A Compositional Generalist-Specialist Framework for Computer Use Agents","created":"2025-04-01","cited_by_count":159,"area":"agents"},{"id":"2504.01990","title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","created":"2025-03-31","cited_by_count":126,"area":"agents"},{"id":"2502.14499","title":"MLGym: A New Framework and Benchmark for Advancing AI Research Agents","created":"2025-02-20","cited_by_count":124,"area":"agents"},{"id":"2501.04682","title":"Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought","created":"2025-01-08","cited_by_count":109,"area":"lr"},{"id":"2501.04575","title":"InfiGUIAgent: A Multimodal Generalist GUI Agent with Native Reasoning and Reflection","created":"2025-01-08","cited_by_count":67,"area":"lr"},{"id":"2507.23361","title":"SWE-Exp: Experience-Driven Software Issue Resolution","created":"2025-07-31","cited_by_count":65,"area":null},{"id":"2504.21024","title":"WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model","created":"2025-04-23","cited_by_count":61,"area":"wm"},{"id":"2410.19609","title":"OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization","created":"2024-10-25","cited_by_count":46,"area":"agents"},{"id":"2502.16707","title":"Reflective Planning: Vision-Language Models for Multi-Stage Long-Horizon Robotic Manipulation","created":"2025-02-23","cited_by_count":42,"area":"mllm"},{"id":"2501.02765","title":"Visual Large Language Models for Generalized and Specialized Applications","created":"2025-01-06","cited_by_count":36,"area":"mllm"},{"id":"2506.07976","title":"Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction","created":"2025-06-09","cited_by_count":34,"area":"lr"},{"id":"2505.00684","title":"Visual Test-time Scaling for GUI Agent Grounding","created":"2025-05-01","cited_by_count":30,"area":"lr"},{"id":"2505.20660","title":"BacktrackAgent: Enhancing GUI Agent with Error Detection and Backtracking Mechanism","created":"2025-05-27","cited_by_count":25,"area":"agents"},{"id":"2502.07942","title":"Symbiotic Cooperation for Web Agents: Harnessing Complementary Strengths of Large and Small LLMs","created":"2025-02-11","cited_by_count":24,"area":"agents"},{"id":"2602.05842","title":"Reinforcement World Model Learning for LLM-based Agents","created":"2026-02-05","cited_by_count":24,"area":"wm"},{"id":"2512.16301","title":"Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills","created":"2025-12-18","cited_by_count":22,"area":"agents"},{"id":"2507.14293","title":"WebGuard: Building a Generalizable Guardrail for Web Agents","created":"2025-07-18","cited_by_count":21,"area":"agents"},{"id":"2502.12130","title":"Scaling Autonomous Agents via Automatic Reward Modeling And Planning","created":"2025-02-17","cited_by_count":19,"area":"lr"},{"id":"2503.20527","title":"StableToolBench-MirrorAPI: Modeling Tool Environments as Mirrors of 7,000+ Real-World APIs","created":"2025-03-26","cited_by_count":14,"area":"agents"},{"id":"2506.00320","title":"Dyna-Think: Synergizing Reasoning, Acting, and World Model Simulation in AI Agents","created":"2025-05-31","cited_by_count":14,"area":"wm"},{"id":"2507.11662","title":"Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification","created":"2025-07-15","cited_by_count":14,"area":"lr"},{"id":"2601.22149","title":"DynaWeb: Model-Based Reinforcement Learning of Web Agents","created":"2026-01-29","cited_by_count":14,"area":"wm"},{"id":"2604.00892","title":"When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation","created":"2026-04-01","cited_by_count":14,"area":"agents"},{"id":"2604.05477","title":"Don't Act Blindly: Robust GUI Automation via Action-Effect Verification and Self-Correction","created":"2026-04-07","cited_by_count":14,"area":"agents"},{"id":"2504.10127","title":"Breaking the Data Barrier -- Building GUI Agents Through Task Generalization","created":"2025-04-14","cited_by_count":13,"area":"agents"},{"id":"2505.21499","title":"AdInject: Real-World Black-Box Attacks on Web Agents via Advertising Delivery","created":"2025-05-27","cited_by_count":10,"area":"agents"},{"id":"2510.09577","title":"Dyna-Mind: Learning to Simulate from Experience for Better AI Agents","created":"2025-10-10","cited_by_count":8,"area":"lr"},{"id":"2412.14860","title":"Think&Cite: Improving Attributed Text Generation with Self-Guided Tree Search and Progress Reward Modeling","created":"2024-12-19","cited_by_count":6,"area":"lr"},{"id":"2506.05213","title":"LLM-First Search: Self-Guided Exploration of the Solution Space","created":"2025-06-05","cited_by_count":6,"area":"lr"},{"id":"2509.05197","title":"AI Agents for Web Testing: A Case Study in the Wild","created":"2025-09-05","cited_by_count":6,"area":"agents"},{"id":"2509.21072","title":"Recon-Act: A Self-Evolving Multi-Agent Browser-Use System via Web Reconnaissance, Tool Generation, and Task Execution","created":"2025-09-25","cited_by_count":5,"area":null},{"id":"2510.19245","title":"See, Think, Act: Online Shopper Behavior Simulation with VLM Agents","created":"2025-10-22","cited_by_count":5,"area":"lr"},{"id":"2503.02878","title":"Language Models can Self-Improve at State-Value Estimation for Better Search","created":"2025-03-04","cited_by_count":4,"area":"synth"},{"id":"2505.18829","title":"LiteCUA: Computer as MCP Server for Computer-Use Agent on AIOS","created":"2025-05-24","cited_by_count":4,"area":"agents"},{"id":"2602.19372","title":"Seeing Farther and Smarter: Value-Guided Multi-Path Reflection for VLM Policy Optimization","created":"2026-02-22","cited_by_count":4,"area":null},{"id":"2605.25707","title":"AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions","created":"2026-05-25","cited_by_count":4,"area":"agents"},{"id":"2606.28971","title":"Self-Evolving Agentic Image Restoration via Deliberate Planning and Intuitive Execution","created":"2026-06-27","cited_by_count":4,"area":"agents"},{"id":"2602.15353","title":"NeuroSymActive: Differentiable Neural-Symbolic Reasoning with Active Exploration for Knowledge Graph Question Answering","created":"2026-02-17","cited_by_count":3,"area":"lr"},{"id":"2603.20366","title":"WebNavigator: Global Web Navigation via Interaction Graph Retrieval","created":"2026-03-20","cited_by_count":3,"area":null},{"id":"2507.03327","title":"Read Quietly, Think Aloud: Decoupling Comprehension and Reasoning in LLMs","created":"2025-07-04","cited_by_count":2,"area":"lr"},{"id":"2602.05810","title":"Bifrost: Steering Strategic Trajectories to Bridge Contextual Gaps for Self-Improving Agents","created":"2026-02-05","cited_by_count":2,"area":"synth"},{"id":"2602.14083","title":"Plan-MCTS: Plan Exploration for Action Exploitation in Web Navigation","created":"2026-02-15","cited_by_count":2,"area":null},{"id":"2605.24785","title":"PANDO: Efficient Multimodal AI Agents via Online Skill Distillation","created":"2026-05-24","cited_by_count":2,"area":"agents"},{"id":"2509.05368","title":"Long-Horizon Visual Imitation Learning via Plan and Code Reflection","created":"2025-09-04","cited_by_count":1,"area":"offlinerl"},{"id":"2510.06274","title":"Bridging Reasoning to Learning: Unmasking Illusions using Complexity Out of Distribution Generalization","created":"2025-10-06","cited_by_count":1,"area":"lr"},{"id":"2605.28224","title":"When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents?","created":"2026-05-27","cited_by_count":1,"area":"lr"},{"id":"2606.05296","title":"Agentic Monte Carlo: Simulating Reinforcement Learning for Black-Box Agents","created":"2026-06-03","cited_by_count":1,"area":"agents"},{"id":"2608.14339","title":"Clearing the Fog: Towards Installing and Refining Proactive Exploration Capabilities in LLM Agents","created":"2026-08-14","cited_by_count":1,"area":"agents"},{"id":"2608.20370","title":"Benchmarking LLM Serving Systems for Agentic AI Workloads with XPerf","created":"2026-06-19","cited_by_count":1,"area":"agents"},{"id":"2506.17779","title":"Toward Autonomous UI Exploration: The UIExplorer Benchmark","created":"2025-06-21","cited_by_count":0,"area":null},{"id":"2510.22781","title":"Agentic Meta-Orchestrator for Multi-task Copilots","created":"2025-10-26","cited_by_count":0,"area":"agents"},{"id":"2604.14345","title":"PAC-CF: Calibrating Irreversible Frontier Pruning in LLM-Guided Search","created":"2026-04-15","cited_by_count":0,"area":null},{"id":"2604.18779","title":"Mango: Multi-Agent Web Navigation via Global-View Optimization","created":"2026-04-20","cited_by_count":0,"area":"agents"},{"id":"2606.11662","title":"TreeSeeker: Tree-Structured Trial, Error, and Return in Deep Search","created":"2026-06-10","cited_by_count":0,"area":null},{"id":"2608.27866","title":"Iron: Intent-Aligned and Retrospective Dual Learning Framework for Enhancing Generalist Virtual Agents","created":"2026-08-28","cited_by_count":0,"area":"agents"},{"id":"2609.33646","title":"Probe to Act: Elevating Browser-Use Agent via Active Visual Probing","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33920","title":"HyperMCTS: Hypergraph-Augmented MCTS for Long-Horizon LLM Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.35366","title":"Planarian: Managing Agent State with Statepoints","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.36201","title":"SCOUT: Synergizing Reasoning and Tool-Use for Computer-Use Safety","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2610.04889","title":"ForkPilot: Self-Evolving Policy for Retrospective Search in Long-Horizon Agents","created":"2026-10-04","cited_by_count":0,"area":"agents"}],"next_cursor":null}