{"total":89,"rows":[{"id":"2507.20534","title":"Kimi K2: Open Agentic Intelligence","created":"2025-07-28","cited_by_count":567,"area":"agents"},{"id":"2501.06322","title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","created":"2025-01-10","cited_by_count":431,"area":"agents"},{"id":"2409.00920","title":"ToolACE: Winning the Points of LLM Function Calling","created":"2024-09-02","cited_by_count":216,"area":"agents"},{"id":"2504.21318","title":"Phi-4-reasoning Technical Report","created":"2025-04-30","cited_by_count":151,"area":"lr"},{"id":"2504.19678","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","created":"2025-04-28","cited_by_count":149,"area":"lr"},{"id":"2502.01600","title":"Reinforcement Learning for Long-Horizon Interactive LLM Agents","created":"2025-02-03","cited_by_count":108,"area":"agents"},{"id":"2502.11357","title":"Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents","created":"2025-02-17","cited_by_count":72,"area":"agents"},{"id":"2505.17612","title":"Distilling LLM Agent into Small Models with Retrieval and Code Tools","created":"2025-05-23","cited_by_count":47,"area":"lr"},{"id":"2602.21193","title":"On Data Engineering for Scaling LLM Terminal Capabilities","created":"2026-02-24","cited_by_count":43,"area":null},{"id":"2412.13337","title":"Unveiling the Secret Recipe: A Guide For Supervised Fine-Tuning Small LLMs","created":"2024-12-17","cited_by_count":40,"area":null},{"id":"2605.10999","title":"SkillGen: Verified Inference-Time Agent Skill Synthesis","created":"2026-05-09","cited_by_count":36,"area":"agents"},{"id":"2511.19663","title":"Fara-7B: An Efficient Agentic Model for Computer Use","created":"2025-11-24","cited_by_count":35,"area":"agents"},{"id":"2602.21320","title":"Tool-R0: Self-Evolving LLM Agents for Tool-Learning from Zero Data","created":"2026-02-24","cited_by_count":34,"area":"agents"},{"id":"2502.06776","title":"InSTA: Towards Internet-Scale Training For Agents","created":"2025-02-10","cited_by_count":32,"area":"agents"},{"id":"2508.18669","title":"MUA-RL: Multi-turn User-interacting Agent Reinforcement Learning for agentic tool use","created":"2025-08-26","cited_by_count":32,"area":"agents"},{"id":"2510.07841","title":"Self-Improving LLM Agents at Test-Time","created":"2025-10-09","cited_by_count":30,"area":"agents"},{"id":"2602.07274","title":"TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents","created":"2026-02-06","cited_by_count":29,"area":"agents"},{"id":"2509.07764","title":"AgentSentinel: An End-to-End and Real-Time Security Defense Framework for Computer-Use Agents","created":"2025-09-09","cited_by_count":27,"area":"agents"},{"id":"2604.06126","title":"Gym-Anything: Turn any Software into an Agent Environment","created":"2026-04-07","cited_by_count":27,"area":"agents"},{"id":"2503.14269","title":"DARS: Dynamic Action Re-Sampling to Enhance Coding Agent Performance by Adaptive Tree Traversal","created":"2025-03-18","cited_by_count":20,"area":"agents"},{"id":"2505.10717","title":"A Modular Approach for Clinical SLMs Driven by Synthetic Data with Pre-Instruction Tuning, Model Merging, and Clinical-Tasks Alignment","created":"2025-05-15","cited_by_count":20,"area":"alignment"},{"id":"2409.15934","title":"Automated test generation to evaluate tool-augmented LLMs as conversational AI agents","created":"2024-09-24","cited_by_count":17,"area":"agents"},{"id":"2510.24702","title":"Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents","created":"2025-10-28","cited_by_count":17,"area":"agents"},{"id":"2511.09148","title":"LoopTool: Closing the Data-Training Loop for Robust LLM Tool Calls","created":"2025-11-12","cited_by_count":17,"area":null},{"id":"2606.25996","title":"Autodata: An agentic data scientist to create high quality synthetic data","created":"2026-06-24","cited_by_count":16,"area":"agents"},{"id":"2409.02098","title":"CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation","created":"2024-09-03","cited_by_count":14,"area":"synth"},{"id":"2505.13772","title":"Krikri: Advancing Open Large Language Models for Greek","created":"2025-05-19","cited_by_count":14,"area":null},{"id":"2511.06101","title":"SynthAgent: Adapting Web Agents with Synthetic Supervision","created":"2025-11-08","cited_by_count":14,"area":"agents"},{"id":"2607.04884","title":"HunyuanOCR-1.5: Making Lightweight OCR VLMs Faster and Better","created":"2026-07-06","cited_by_count":14,"area":"mllm"},{"id":"2412.08445","title":"TapeAgents: a Holistic Framework for Agent Development and Optimization","created":"2024-12-11","cited_by_count":13,"area":"agents"},{"id":"2412.17149","title":"A Multi-AI Agent System for Autonomous Optimization of Agentic AI Solutions via Iterative Refinement and LLM-Driven Feedback Loops","created":"2024-12-22","cited_by_count":13,"area":"agents"},{"id":"2603.11076","title":"DIVE: Scaling Diversity in Agentic Task Synthesis for Generalizable Tool Use","created":"2026-03-10","cited_by_count":13,"area":"agents"},{"id":"2412.04494","title":"MAG-V: A Multi-Agent Framework for Synthetic Data Generation and Verification","created":"2024-11-28","cited_by_count":12,"area":"agents"},{"id":"2502.05439","title":"Agentic AI Systems Applied to tasks in Financial Services: Modeling and model risk management crews","created":"2025-02-08","cited_by_count":12,"area":"agents"},{"id":"2512.16149","title":"ToolForge: A Data Synthesis Pipeline for Multi-Hop Search without Real-World APIs","created":"2025-12-18","cited_by_count":10,"area":"agents"},{"id":"2504.12322","title":"A Strategic Coordination Framework of Small LLMs Matches Large LLMs in Data Synthesis","created":"2025-04-11","cited_by_count":9,"area":"synth"},{"id":"2410.04524","title":"Toward Secure Tuning: Mitigating Security Risks from Instruction Fine-Tuning","created":"2024-10-06","cited_by_count":8,"area":null},{"id":"2508.18255","title":"Hermes 4 Technical Report","created":"2025-08-25","cited_by_count":8,"area":"lr"},{"id":"2601.15793","title":"HumanLLM: Towards Personalized Understanding and Simulation of Human Nature","created":"2026-01-22","cited_by_count":8,"area":null},{"id":"2604.14116","title":"TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration","created":"2026-04-15","cited_by_count":8,"area":"agents"},{"id":"2605.10832","title":"Towards On-Policy Data Evolution for Visual-Native Multimodal Deep Search Agents","created":"2026-05-11","cited_by_count":8,"area":"lr"},{"id":"2412.17743","title":"YuLan-Mini: An Open Data-efficient Language Model","created":"2024-12-23","cited_by_count":7,"area":null},{"id":"2506.11117","title":"ScIRGen: Synthesize Realistic and Large-Scale RAG Dataset for Scientific Research","created":"2025-06-09","cited_by_count":7,"area":null},{"id":"2509.06795","title":"Anchoring Refusal Direction: Mitigating Safety Risks in Tuning via Projection Constraint","created":"2025-09-08","cited_by_count":7,"area":null},{"id":"2510.19361","title":"AgenticMath: Enhancing LLM Reasoning via Agentic-based Math Data Generation","created":"2025-10-22","cited_by_count":7,"area":"lr"},{"id":"2510.21910","title":"Adversarial D\\'ej\\`a Vu: Jailbreak Dictionary Learning for Stronger Generalization to Unseen Attacks","created":"2025-10-24","cited_by_count":7,"area":"safety"},{"id":"2604.11741","title":"Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games","created":"2026-04-13","cited_by_count":6,"area":"lr"},{"id":"2609.00006","title":"Harness Engineering: Anatomy, Architecture, and Evolution of Coding Agents -- A Source-Code Study of Eleven Systems","created":"2026-07-15","cited_by_count":6,"area":"agents"},{"id":"2507.22080","title":"CodeEvo: Interaction-Driven Synthesis of Code-centric Data through Hybrid and Iterative Feedback","created":"2025-07-25","cited_by_count":5,"area":null},{"id":"2510.03777","title":"GuidedSampling: Steering LLMs Towards Diverse Candidate Solutions at Inference-Time","created":"2025-10-04","cited_by_count":5,"area":null},{"id":"2512.09081","title":"AgentComp: From Agentic Reasoning to Compositional Mastery in Text-to-Image Models","created":"2025-12-09","cited_by_count":5,"area":"lr"},{"id":"2602.03219","title":"Beyond Quantity: Trajectory Diversity Scaling for Code Agents","created":"2026-02-03","cited_by_count":5,"area":"agents"},{"id":"2502.00808","title":"Synthetic Artifact Auditing: Tracing LLM-Generated Synthetic Data Usage in Downstream Applications","created":"2025-02-02","cited_by_count":4,"area":"synth"},{"id":"2503.01493","title":"Sherkala-Chat: Building a State-of-the-Art LLM for Kazakh in a Moderately Resourced Setting","created":"2025-03-03","cited_by_count":4,"area":null},{"id":"2505.18458","title":"A Survey of LLM $\\times$ DATA","created":"2025-05-24","cited_by_count":4,"area":"rag"},{"id":"2506.05766","title":"BioMol-MQA: A Multi-Modal Question Answering Dataset For LLM Reasoning Over Bio-Molecular Interactions","created":"2025-06-06","cited_by_count":4,"area":"lr"},{"id":"2506.13109","title":"Leveraging In-Context Learning for Language Model Agents","created":"2025-06-16","cited_by_count":4,"area":"agents"},{"id":"2509.21294","title":"UPDESH: Synthesizing Grounded Instruction Tuning Data for 13 Indic Languages","created":"2025-09-25","cited_by_count":4,"area":null},{"id":"2601.09733","title":"Closing the Data Loop: Using OpenDataArena to Engineer Superior Training Datasets","created":"2025-12-30","cited_by_count":4,"area":null},{"id":"2608.14312","title":"Envs-FORGE: Frontier-Optimized Reward-Grounded Environment Synthesis for Agent RL","created":"2026-08-14","cited_by_count":4,"area":"lr"},{"id":"2606.31537","title":"DataEvolver: Self-Evolving Multi-Agent Data Construction for Text-Rich Image Generation","created":"2026-06-30","cited_by_count":3,"area":null},{"id":"2410.18146","title":"Meaning Typed Prompting: A Technique for Efficient, Reliable Structured Output Generation","created":"2024-10-22","cited_by_count":2,"area":null},{"id":"2412.07786","title":"Towards Agentic Schema Refinement","created":"2024-11-25","cited_by_count":2,"area":"agents"},{"id":"2501.01834","title":"MoColl: Agent-Based Specific and General Model Collaboration for Image Captioning","created":"2025-01-03","cited_by_count":2,"area":"agents"},{"id":"2502.11573","title":"InfiR : Crafting Effective Small Language Models and Multimodal Small Language Models in Reasoning","created":"2025-02-17","cited_by_count":2,"area":"lr"},{"id":"2504.14523","title":"Learning from Reasoning Failures via Synthetic Data Generation","created":"2025-04-20","cited_by_count":2,"area":null},{"id":"2510.00078","title":"Adaptive and Resource-efficient Agentic AI Systems for Mobile and Embedded Devices: A Survey","created":"2025-09-30","cited_by_count":2,"area":"lr"},{"id":"2601.08225","title":"User-Oriented Multi-Turn Dialogue Generation with Tool Use at scale","created":"2026-01-13","cited_by_count":2,"area":"lr"},{"id":"2606.14179","title":"CacheRL:Multi-Turn Tool-Calling Agents via Cached Rollouts and Hybrid Reward","created":"2026-06-12","cited_by_count":2,"area":"agents"},{"id":"2504.05607","title":"FactGuard: Leveraging Multi-Agent Systems to Generate Answerable and Unanswerable Questions for Enhanced Long-Context LLM Extraction","created":"2025-04-08","cited_by_count":1,"area":"agents"},{"id":"2505.18011","title":"Training with Pseudo-Code for Instruction Following","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2505.22157","title":"LASER: Stratified Selective Sampling for Instruction Tuning with Dedicated Scoring Strategy","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2506.07691","title":"Breaking the Block: Preserving Data Continuity to Train Superior SAEs for Instruct Models","created":"2025-06-09","cited_by_count":1,"area":"mechinterp"},{"id":"2510.21970","title":"Performance Trade-offs of Optimizing Small Language Models for E-Commerce","created":"2025-10-24","cited_by_count":1,"area":null},{"id":"2601.22159","title":"RedSage: A Cybersecurity Generalist LLM","created":"2026-01-29","cited_by_count":1,"area":null},{"id":"2604.21637","title":"Multilinguality at the Edge: Developing Language Models for the Global South","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2606.07710","title":"WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing","created":"2026-06-05","cited_by_count":1,"area":"agents"},{"id":"2606.11127","title":"Provenance-Grounded Gating and Adaptive Recovery in Synthetic Post-Training Data Curation","created":"2026-06-09","cited_by_count":1,"area":"alignment"},{"id":"2606.11520","title":"ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories","created":"2026-06-09","cited_by_count":1,"area":"agents"},{"id":"2607.16204","title":"Masked Diffusion Language Models are Strong and Steerable Text-Based World Models for Agentic RL","created":"2026-05-07","cited_by_count":1,"area":"wm"},{"id":"2608.05144","title":"Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2602.20296","title":"Learning to Solve Complex Problems via Dataset Decomposition","created":"2026-02-23","cited_by_count":0,"area":null},{"id":"2606.09138","title":"Claw-R1: A Step-Level Data Middleware System for Agentic Reinforcement Learning","created":"2026-06-08","cited_by_count":0,"area":"agents"},{"id":"2606.21337","title":"DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams","created":"2026-06-19","cited_by_count":0,"area":"agents"},{"id":"2609.18417","title":"Dependency-Aware Trajectory Refinement for Efficient Multi-Turn Agent Fine-Tuning","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.22592","title":"AutoGym: Blueprint-First Generation of Verifiable Agent Gyms","created":"2026-09-18","cited_by_count":0,"area":"agents"},{"id":"2610.00779","title":"Effective Synthetic Data Curation Requires Group-Level Signals","created":"2026-09-30","cited_by_count":0,"area":"synth"},{"id":"2610.07004","title":"Topology-Consistent Task Planning over Cellular Workflow Complexes for LLM-based Agents","created":"2026-10-04","cited_by_count":0,"area":"agents"},{"id":"2610.12274","title":"HarnessSQL: Harness-Native Training for SQL Agents in Realistic Database Environments","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}