{"total":62,"rows":[{"id":"2604.08224","title":"Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering","created":"2026-04-09","cited_by_count":74,"area":"agents"},{"id":"2510.08049","title":"A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models","created":"2025-10-09","cited_by_count":38,"area":"lr"},{"id":"2510.18821","title":"Search Self-play: Pushing the Frontier of Agent Capability without Supervision","created":"2025-10-21","cited_by_count":34,"area":"agents"},{"id":"2509.22558","title":"StepORLM: A Self-Evolving Framework With Generative Process Supervision For Operations Research Language Models","created":"2025-09-26","cited_by_count":26,"area":"alignment"},{"id":"2510.16724","title":"A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications","created":"2025-10-19","cited_by_count":22,"area":"rag"},{"id":"2510.20168","title":"DeepWideSearch: Benchmarking Depth and Width in Agentic Information Seeking","created":"2025-10-23","cited_by_count":21,"area":"agents"},{"id":"2601.01592","title":"OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs","created":"2026-01-04","cited_by_count":21,"area":"mllm"},{"id":"2510.08276","title":"Beyond Turn Limits: Training Deep Search Agents with Dynamic Context Window","created":"2025-10-09","cited_by_count":19,"area":"lr"},{"id":"2508.16279","title":"AgentScope 1.0: A Developer-Centric Framework for Building Agentic Applications","created":"2025-08-22","cited_by_count":17,"area":"agents"},{"id":"2602.14878","title":"Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions","created":"2026-02-16","cited_by_count":17,"area":"agents"},{"id":"2607.13988","title":"TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents","created":"2026-07-15","cited_by_count":16,"area":null},{"id":"2509.06733","title":"Reinforcement Learning Foundations for Deep Research Systems: A Survey","created":"2025-09-08","cited_by_count":14,"area":"lr"},{"id":"2510.24397","title":"APTBench: Benchmarking Agentic Potential of Base LLMs During Pre-Training","created":"2025-10-28","cited_by_count":11,"area":"agents"},{"id":"2603.16104","title":"Efficient LLM Serving for Agentic Workflows: A Data Systems Perspective","created":"2026-03-17","cited_by_count":11,"area":"agents"},{"id":"2604.12890","title":"Towards Long-horizon Agentic Multimodal Search","created":"2026-04-14","cited_by_count":11,"area":"agents"},{"id":"2508.04026","title":"VeriWeb: Verifiable Long-Chain Web Benchmark for Agentic Information-Seeking","created":"2025-08-06","cited_by_count":10,"area":"agents"},{"id":"2509.21826","title":"ResT: Reshaping Token-Level Policy Gradients for Tool-Use Large Language Models","created":"2025-09-26","cited_by_count":10,"area":null},{"id":"2605.16986","title":"Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents","created":"2026-05-16","cited_by_count":10,"area":"lr"},{"id":"2604.07466","title":"Cross-Tokenizer LLM Distillation through a Byte-Level Interface","created":"2026-04-08","cited_by_count":8,"area":null},{"id":"2509.22391","title":"Do LLM Agents Know How to Ground, Recover, and Assess? A Benchmark for Epistemic Competence in Information-Seeking Agents","created":"2025-09-26","cited_by_count":7,"area":"agents"},{"id":"2510.09686","title":"Stop DDoS Attacking the Research Community with AI-Generated Survey Papers","created":"2025-10-09","cited_by_count":7,"area":null},{"id":"2510.15339","title":"AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction","created":"2025-10-17","cited_by_count":7,"area":"lr"},{"id":"2510.00861","title":"Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs","created":"2025-10-01","cited_by_count":6,"area":"lr"},{"id":"2602.08543","title":"GISA: A Benchmark for General Information-Seeking Assistant","created":"2026-02-09","cited_by_count":6,"area":null},{"id":"2509.23694","title":"SafeSearch: Automated Red-Teaming of LLM-Based Search Agents","created":"2025-09-28","cited_by_count":4,"area":"agents"},{"id":"2510.14703","title":"ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling","created":"2025-10-16","cited_by_count":4,"area":"agents"},{"id":"2604.10741","title":"Deep-Reporter: Deep Research for Grounded Multimodal Long-Form Generation","created":"2026-04-12","cited_by_count":4,"area":"agents"},{"id":"2604.10938","title":"AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic Web","created":"2026-04-13","cited_by_count":4,"area":"agents"},{"id":"2605.02910","title":"CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing","created":"2026-04-06","cited_by_count":4,"area":"lr"},{"id":"2604.04949","title":"Learning to Retrieve from Agent Trajectories","created":"2026-03-30","cited_by_count":3,"area":"agents"},{"id":"2605.29861","title":"Towards Verifiable Multimodal Deep Research: A Multi-Agent Harness for Interleaved Report Generation","created":"2026-05-28","cited_by_count":3,"area":"agents"},{"id":"2606.03239","title":"ARBOR: Online Process Rewards via a Reusable Rubric Buffer for Search Agents","created":"2026-06-02","cited_by_count":3,"area":"agents"},{"id":"2603.01493","title":"PhotoBench: Beyond Visual Matching Towards Personalized Intent-Driven Photo Retrieval","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.03790","title":"T2S-Bench & Structure-of-Thought: Benchmarking and Prompting Comprehensive Text-to-Structure Reasoning","created":"2026-03-04","cited_by_count":2,"area":"lr"},{"id":"2605.09915","title":"Position: Academic Conferences are Potentially Facing Denominator Gaming Caused by Fully Automated Scientific Agents","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2605.13486","title":"R^2-Mem: Reflective Experience for Memory Search","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2608.01913","title":"Diagnosing Search Behavior and Failure Modes in Long-Horizon Search Agents","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2608.24794","title":"CAFE: Self-Improving Search Agents Need Co-Evolving Feedback","created":"2026-08-25","cited_by_count":2,"area":"alignment"},{"id":"2609.00813","title":"One Policy, Any Budget: Internalizing Budget-Aware Search via Reinforcement Learning","created":"2026-09-01","cited_by_count":2,"area":"lr"},{"id":"2601.08403","title":"Owen-Shapley Policy Optimization: A Principled RL Algorithm for Generative Search LLMs","created":"2026-01-13","cited_by_count":1,"area":"lr"},{"id":"2603.28361","title":"Deep Research of Deep Research: From Transformer to Agent, From AI to AI for Science","created":"2026-03-30","cited_by_count":1,"area":"lr"},{"id":"2604.05952","title":"Towards Trustworthy Report Generation: A Deep Research Agent with Progressive Confidence Estimation and Calibration","created":"2026-04-07","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":"2605.00043","title":"SiriusHelper: An LLM Agent-Based Operations Assistant for Big Data Platforms","created":"2026-04-29","cited_by_count":1,"area":"agents"},{"id":"2605.10488","title":"DeepRefine: Agentic Knowledge Refinement via Reinforcement Learning","created":"2026-05-11","cited_by_count":1,"area":"agents"},{"id":"2606.27669","title":"When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search","created":"2026-06-26","cited_by_count":1,"area":"agents"},{"id":"2607.08662","title":"WebSwarm: Recursive Multi-Agent Orchestration for Deep-and-Wide Web Search","created":"2026-07-09","cited_by_count":1,"area":"agents"},{"id":"2608.02097","title":"Fetch-then-Explore: Decoupling Selection from Extraction over a Persistent Workspace for Search Agents","created":"2026-08-03","cited_by_count":1,"area":null},{"id":"2601.02574","title":"Fact-Checking with Large Language Models via Probabilistic Certainty and Consistency","created":"2026-01-05","cited_by_count":0,"area":null},{"id":"2603.27065","title":"Story2Proposal: A Scaffold for Structured Scientific Paper Writing","created":"2026-03-28","cited_by_count":0,"area":null},{"id":"2605.13534","title":"Scaling Retrieval-Augmented Reasoning with Parallel Search and Explicit Merging","created":"2026-05-13","cited_by_count":0,"area":"lr"},{"id":"2605.29555","title":"From Blind Guess to Informed Judgment: Teaching LLMs to Evaluate Materials by Building Knowledge-Augmented Preference Signals","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.12871","title":"DailyReport: An Open-ended Benchmark for Evaluating Search Agents on Daily Search Tasks","created":"2026-06-11","cited_by_count":0,"area":"agents"},{"id":"2607.06374","title":"VaseMuseum: Digital Intelligent Museum for Ancient Greek Pottery","created":"2026-07-07","cited_by_count":0,"area":"mllm"},{"id":"2608.01867","title":"CRISP: Critical Step Perception for Training Efficient Deep Search Agents","created":"2026-08-03","cited_by_count":0,"area":"agents"},{"id":"2608.04565","title":"Breadcrumbing Search Agents","created":"2026-08-05","cited_by_count":0,"area":"agents"},{"id":"2609.00865","title":"MemoryWalker: Stop Training Agents on Contexts They Never Saw","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.08887","title":"Q2D-Web: A Large-Scale Benchmark for Retrieval in Agentic RAG Systems","created":"2026-09-08","cited_by_count":0,"area":"rag"},{"id":"2610.07023","title":"Beyond Refusal Patterns: Safe-Role Internalization for Robust and Generalizable LLM Safety Alignment","created":"2026-10-04","cited_by_count":0,"area":"alignment"},{"id":"2610.16998","title":"Glasseek: A Transparent Recipe for Training and Trustworthy Evaluation of DeepSearch Agents","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.17726","title":"TSRL: Trigger-based Supervised Reinforcement Learning for Continual Agent Training","created":"2026-10-13","cited_by_count":0,"area":"lr"},{"id":"2610.17827","title":"Benchmarking and Training Reward Models for Cross-Source Evidence Grounding in Search Agents","created":"2026-10-13","cited_by_count":0,"area":"alignment"}],"next_cursor":null}