{"total":108,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2505.10468","title":"AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges","created":"2025-05-15","cited_by_count":169,"area":"agents"},{"id":"2507.13334","title":"A Survey of Context Engineering for Large Language Models","created":"2025-07-17","cited_by_count":126,"area":null},{"id":"2602.12430","title":"Agent Skills for Large Language Models: Architecture, Acquisition, Security, and the Path Forward","created":"2026-02-12","cited_by_count":113,"area":"agents"},{"id":"2509.01055","title":"VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Use","created":"2025-09-01","cited_by_count":96,"area":"lr"},{"id":"2507.06134","title":"OpenAgentSafety: A Comprehensive Framework for Evaluating Real-World AI Agent Safety","created":"2025-07-08","cited_by_count":75,"area":"agents"},{"id":"2510.25445","title":"Agentic AI: A Comprehensive Survey of Architectures, Applications, and Future Directions","created":"2025-10-29","cited_by_count":48,"area":"agents"},{"id":"2512.04123","title":"Measuring Agents in Production","created":"2025-12-02","cited_by_count":37,"area":"agents"},{"id":"2504.18875","title":"Generative to Agentic AI: Survey, Conceptualization, and Challenges","created":"2025-04-26","cited_by_count":33,"area":"agents"},{"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":"2510.23482","title":"On the Faithfulness of Visual Thinking: Measurement and Enhancement","created":"2025-10-27","cited_by_count":17,"area":"lr"},{"id":"2602.13272","title":"TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Tasks","created":"2026-02-05","cited_by_count":17,"area":"agents"},{"id":"2507.02097","title":"The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems","created":"2025-07-02","cited_by_count":14,"area":"agents"},{"id":"2602.21534","title":"ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning","created":"2026-02-25","cited_by_count":13,"area":"agents"},{"id":"2601.03715","title":"R$^3$L: Reflect-then-Retry Reinforcement Learning with Language-Guided Exploration, Pivotal Credit, and Positive Amplification","created":"2026-01-07","cited_by_count":12,"area":"lr"},{"id":"2505.07064","title":"ParaView-MCP: An Autonomous Visualization Agent with Direct Tool Use","created":"2025-05-11","cited_by_count":11,"area":"agents"},{"id":"2512.01311","title":"CuES: A Curiosity-driven and Environment-grounded Synthesis Framework for Agentic RL","created":"2025-12-01","cited_by_count":10,"area":"agents"},{"id":"2512.24618","title":"Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models","created":"2025-12-31","cited_by_count":10,"area":"agents"},{"id":"2509.25299","title":"ID-RAG: Identity Retrieval-Augmented Generation for Long-Horizon Persona Coherence in Generative Agents","created":"2025-09-29","cited_by_count":7,"area":"rag"},{"id":"2510.11184","title":"Reinforcement Learning for Tool-Integrated Interleaved Thinking towards Cross-Domain Generalization","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2606.08755","title":"Co-Evolving Skill Generation and Policy Optimization","created":"2026-06-07","cited_by_count":7,"area":null},{"id":"2606.09071","title":"REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces","created":"2026-06-08","cited_by_count":7,"area":"agents"},{"id":"2508.01012","title":"AutoEDA: Enabling EDA Flow Automation through Microservice-Based LLM Agents","created":"2025-08-01","cited_by_count":6,"area":"agents"},{"id":"2510.19838","title":"Branch-and-Browse: Efficient and Controllable Web Exploration with Tree-Structured Reasoning and Action Memory","created":"2025-10-18","cited_by_count":6,"area":"lr"},{"id":"2603.12109","title":"On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents","created":"2026-03-12","cited_by_count":6,"area":"lr"},{"id":"2505.21537","title":"OpenReview Should be Protected and Leveraged as a Community Asset for Research in the Era of Large Language Models","created":"2025-05-24","cited_by_count":5,"area":null},{"id":"2602.02039","title":"Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models","created":"2026-02-02","cited_by_count":5,"area":"agents"},{"id":"2604.20051","title":"Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text","created":"2026-04-21","cited_by_count":5,"area":"synth"},{"id":"2606.23664","title":"MAS-PromptBench: When Does Prompt Optimization Improve Multi-Agent LLM Systems?","created":"2026-06-22","cited_by_count":5,"area":"agents"},{"id":"2607.04293","title":"CausalGame: Benchmarking Causal Thinking of LLM Agents in Games","created":"2026-07-05","cited_by_count":5,"area":"lr"},{"id":"2510.12264","title":"Reducing Belief Deviation in Reinforcement Learning for Active Reasoning","created":"2025-10-14","cited_by_count":4,"area":"lr"},{"id":"2601.02749","title":"The Path Ahead for Agentic AI: Challenges and Opportunities","created":"2026-01-06","cited_by_count":4,"area":"agents"},{"id":"2601.19752","title":"Agentic Design Patterns: A System-Theoretic Framework","created":"2026-01-27","cited_by_count":4,"area":"agents"},{"id":"2603.22206","title":"Chimera: Latency- and Performance-Aware Multi-agent Serving for Heterogeneous LLMs","created":"2026-03-23","cited_by_count":4,"area":"agents"},{"id":"2603.25747","title":"BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments","created":"2026-01-30","cited_by_count":4,"area":"agents"},{"id":"2608.05013","title":"OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents","created":"2026-08-04","cited_by_count":4,"area":"agents"},{"id":"2505.19764","title":"Multi-View Encoders for Performance Prediction in LLM-Based Agentic Workflows","created":"2025-05-26","cited_by_count":3,"area":"agents"},{"id":"2508.09823","title":"KonfAI: A Modular and Fully Configurable Framework for Deep Learning in Medical Imaging","created":"2025-08-13","cited_by_count":3,"area":null},{"id":"2508.19988","title":"AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios","created":"2025-08-27","cited_by_count":3,"area":"lr"},{"id":"2510.26699","title":"Using Copilot Agent Mode to Automate Library Migration: A Quantitative Assessment","created":"2025-10-30","cited_by_count":3,"area":"agents"},{"id":"2602.00169","title":"Towards Agentic Intelligence for Materials Science","created":"2026-01-29","cited_by_count":3,"area":"agents"},{"id":"2602.05877","title":"Agent2Agent Threats in Safety-Critical LLM Assistants: A Human-Centric Taxonomy","created":"2026-02-05","cited_by_count":3,"area":"agents"},{"id":"2603.14575","title":"CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad","created":"2026-03-15","cited_by_count":3,"area":null},{"id":"2605.19717","title":"Physics-in-the-Loop: A Hybrid Agentic Architecture for Validated CAD Engineering Design","created":"2026-05-19","cited_by_count":3,"area":"agents"},{"id":"2605.25604","title":"DVAO: Dynamic Variance-adaptive Advantage Optimization for Multi-reward Reinforcement Learning","created":"2026-05-25","cited_by_count":3,"area":"alignment"},{"id":"2606.17838","title":"Environment-Grounded Automated Prompt Optimization for LLM Game Agents","created":"2026-06-16","cited_by_count":3,"area":"agents"},{"id":"2506.19095","title":"Baba is LLM: Reasoning in a Game with Dynamic Rules","created":"2025-06-23","cited_by_count":2,"area":"lr"},{"id":"2507.08584","title":"To Trade or Not to Trade: An Agentic Approach to Estimating Market Risk Improves Trading Decisions","created":"2025-07-11","cited_by_count":2,"area":"agents"},{"id":"2507.21823","title":"An Agentic AI for a New Paradigm in Business Process Development","created":"2025-07-29","cited_by_count":2,"area":"agents"},{"id":"2509.07122","title":"Neuro-Symbolic Frameworks: Conceptual Characterization and Empirical Comparative Analysis","created":"2025-09-08","cited_by_count":2,"area":null},{"id":"2509.24250","title":"Interactive Program Synthesis for Modeling Collaborative Physical Activities from Narrated Demonstrations","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2511.13726","title":"Refine Thought: A Test-Time Inference Method for Embedding Model Reasoning","created":"2025-10-14","cited_by_count":2,"area":"lr"},{"id":"2603.23279","title":"Emergence of Fragility in LLM-based Social Networks: the Case of Moltbook","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2606.16774","title":"OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models","created":"2026-06-15","cited_by_count":2,"area":"agents"},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2607.02345","title":"SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2505.06817","title":"Control Plane as a Tool: A Scalable Design Pattern for Agentic AI Systems","created":"2025-05-11","cited_by_count":1,"area":"agents"},{"id":"2505.10714","title":"GeoGrid-Bench: Can Foundation Models Understand Multimodal Gridded Geo-Spatial Data?","created":"2025-05-15","cited_by_count":1,"area":null},{"id":"2509.00132","title":"CoComposer: LLM Multi-agent Collaborative Music Composition","created":"2025-08-29","cited_by_count":1,"area":"agents"},{"id":"2510.17995","title":"FABRIC: Framework for Agent-Based Realistic Intelligence Creation","created":"2025-10-20","cited_by_count":1,"area":"agents"},{"id":"2511.14780","title":"Ask WhAI:Probing Belief Formation in Role-Primed LLM Agents","created":"2025-11-06","cited_by_count":1,"area":"agents"},{"id":"2601.12945","title":"A Component-Based Survey of Interactions between Large Language Models and Multi-Armed Bandits","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2602.04813","title":"Agentic AI in Healthcare & Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-based Agents","created":"2026-02-04","cited_by_count":1,"area":"agents"},{"id":"2602.24068","title":"A Novel Hierarchical Multi-Agent System for Payments Using LLMs","created":"2026-02-27","cited_by_count":1,"area":"agents"},{"id":"2603.05485","title":"Towards Provably Unbiased LLM Judges via Bias-Bounded Evaluation","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.13853","title":"APEX-Searcher: Refining Credit Assignment with Subgoaling for Agentic Retrieval-Augmented Generation","created":"2026-03-14","cited_by_count":1,"area":"rag"},{"id":"2603.16876","title":"Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation","created":"2026-02-17","cited_by_count":1,"area":"agents"},{"id":"2603.19347","title":"Exploring the Agentic Frontier of Verilog Code Generation","created":"2026-03-19","cited_by_count":1,"area":"agents"},{"id":"2603.25176","title":"Prompt Attack Detection with LLM-as-a-Judge and Mixture-of-Models","created":"2026-03-26","cited_by_count":1,"area":"safety"},{"id":"2603.28106","title":"InconLens: Interactive Visual Diagnosis of Behavioral Inconsistencies in LLM-based Agentic Systems","created":"2026-03-30","cited_by_count":1,"area":"agents"},{"id":"2604.13242","title":"On the Creativity of AI Agents","created":"2026-04-14","cited_by_count":1,"area":"agents"},{"id":"2604.20855","title":"Caesar: Deep Agentic Web Exploration for Creative Answer Synthesis","created":"2026-02-24","cited_by_count":1,"area":"agents"},{"id":"2604.27859","title":"Rethinking Agentic Reinforcement Learning In Large Language Models","created":"2026-04-30","cited_by_count":1,"area":"lr"},{"id":"2605.02592","title":"Foundation-Model-Based Agents in Industrial Automation: Purposes, Capabilities, and Open Challenges","created":"2026-05-04","cited_by_count":1,"area":"agents"},{"id":"2606.05531","title":"Almieyar-Oryx-BloomBench: A Bilingual Multimodal Benchmark for Cognitively Informed Evaluation of Vision-Language Models","created":"2026-06-04","cited_by_count":1,"area":"lr"},{"id":"2606.06566","title":"NTILC: Neural Tool Invocation via Learned Compression","created":"2026-06-04","cited_by_count":1,"area":"agents"},{"id":"2609.00296","title":"Toward Workflow-Aware Benchmarking for Healthcare NLP Agents","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2508.20637","title":"GDS Agent for Graph Algorithmic Reasoning","created":"2025-08-28","cited_by_count":0,"area":"lr"},{"id":"2509.04847","title":"Collaboration and Conflict between Humans and Language Models through the Lens of Game Theory","created":"2025-09-05","cited_by_count":0,"area":null},{"id":"2510.17301","title":"Comprehending Spatio-temporal Data via Cinematic Storytelling using Large Language Models","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2511.00450","title":"SmartDoc: A Context-Aware Agentic Method Comment Generation Plugin","created":"2025-11-01","cited_by_count":0,"area":"agents"},{"id":"2511.19115","title":"AI Consciousness and Existential Risk","created":"2025-11-24","cited_by_count":0,"area":null},{"id":"2512.10313","title":"EpiPlanAgent: Agentic Automated Epidemic Response Planning","created":"2025-12-11","cited_by_count":0,"area":"agents"},{"id":"2512.22790","title":"ChatGraPhT: A Visual Conversation Interface for Multi-Path Reflection with Agentic LLM Support","created":"2025-12-28","cited_by_count":0,"area":"agents"},{"id":"2601.18401","title":"Superlinear Multi-Step Attention","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2602.15858","title":"State Design Matters: How Representations Shape Dynamic Reasoning in Large Language Models","created":"2026-01-25","cited_by_count":0,"area":"lr"},{"id":"2603.02519","title":"Agentic Mixed-Source Multi-Modal Misinformation Detection with Adaptive Test-Time Scaling","created":"2026-03-03","cited_by_count":0,"area":"lr"},{"id":"2605.03215","title":"Enwar 3.0: An Agentic Multi-Modal LLM Orchestrator for Situation-Aware Beamforming, Blockage Prediction, and Handover Management","created":"2026-05-04","cited_by_count":0,"area":"agents"},{"id":"2606.06820","title":"SCALE: Scalable Cross-Attention Learning with Extrapolation for Agentic Workflow Scheduling","created":"2026-06-05","cited_by_count":0,"area":"agents"},{"id":"2606.16009","title":"Bridging the Usability Gap: Lessons from Interpreting Studies for Machine Interpreting Design","created":"2026-06-14","cited_by_count":0,"area":null},{"id":"2606.16987","title":"Consensus-based Agentic Large Language Model Framework for Harmonized Tariff Schedule Code Classification","created":"2026-06-15","cited_by_count":0,"area":"agents"},{"id":"2606.27136","title":"Joint Learning of Experiential Rules and Policies for Large Language Model Agents","created":"2026-06-25","cited_by_count":0,"area":"agents"},{"id":"2606.29556","title":"Persona-Trained Monte Carlo: Estimating Market-Outcome Distributions via Swarms of Persona-Conditioned Neural Policy Bots in a Limit Order Book","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.07178","title":"Entropy Pacing Policy Optimization for Multi-Task Agentic Reinforcement Learning","created":"2026-07-08","cited_by_count":0,"area":"agents"},{"id":"2607.09403","title":"Fictional Worldbuilding: Multi-Agent LLM Collaboration with Hierarchical Context Compression and Iterative Review","created":"2026-07-10","cited_by_count":0,"area":"agents"},{"id":"2607.14642","title":"MCPEvol-Bench: Benchmarking LLM Agent Performance Across Dynamic Evolutions of MCP Servers","created":"2026-07-16","cited_by_count":0,"area":"agents"},{"id":"2608.02553","title":"A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AI","created":"2026-08-03","cited_by_count":0,"area":"agents"},{"id":"2608.04646","title":"Evaluating Theory of Mind in Reasoning Models: Robustness over Reasoning","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2608.05124","title":"Chained Recursive Language Models for Multi-Iteration Reasoning","created":"2026-08-05","cited_by_count":0,"area":"lr"},{"id":"2608.05857","title":"Mapping Similarity Spaces across Embedding Models with Synthetic Query Probing","created":"2026-08-06","cited_by_count":0,"area":"rag"}],"next_cursor":"100"}