{"total":182,"rows":[{"id":"2606.09498","title":"Self-Harness: Harnesses That Improve Themselves","created":"2026-06-08","cited_by_count":107,"area":"agents"},{"id":"2504.15228","title":"A Self-Improving Coding Agent","created":"2025-04-21","cited_by_count":79,"area":"agents"},{"id":"2508.14111","title":"From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery","created":"2025-08-18","cited_by_count":77,"area":"agents"},{"id":"2507.02554","title":"AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench","created":"2025-07-03","cited_by_count":71,"area":"agents"},{"id":"2508.12752","title":"Deep Research: A Survey of Autonomous Research Agents","created":"2025-08-18","cited_by_count":66,"area":"agents"},{"id":"2505.19955","title":"MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research","created":"2025-05-26","cited_by_count":64,"area":"agents"},{"id":"2506.04133","title":"TRiSM for Agentic AI: A Review of Trust, Risk, and Security Management in LLM-based Agentic Multi-Agent Systems","created":"2025-06-04","cited_by_count":59,"area":"agents"},{"id":"2605.18747","title":"Code as Agent Harness","created":"2026-05-18","cited_by_count":47,"area":"agents"},{"id":"2508.15804","title":"ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks","created":"2025-08-14","cited_by_count":38,"area":"agents"},{"id":"2602.06855","title":"AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents","created":"2026-02-06","cited_by_count":38,"area":"agents"},{"id":"2606.19980","title":"ENPIRE: Agentic Robot Policy Self-Improvement in the Real World","created":"2026-06-18","cited_by_count":38,"area":"agents"},{"id":"2508.21148","title":"A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers","created":"2025-08-28","cited_by_count":37,"area":"agents"},{"id":"2510.07172","title":"NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents","created":"2025-10-08","cited_by_count":36,"area":"agents"},{"id":"2602.17753","title":"The 2025 AI Agent Index: Documenting Technical and Safety Features of Deployed Agentic AI Systems","created":"2026-02-19","cited_by_count":30,"area":"agents"},{"id":"2504.09702","title":"MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?","created":"2025-04-13","cited_by_count":28,"area":"agents"},{"id":"2505.15047","title":"PiFlow: Principle-Aware Scientific Discovery with Multi-Agent Collaboration","created":"2025-05-21","cited_by_count":28,"area":"agents"},{"id":"2602.08990","title":"InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery","created":"2026-02-09","cited_by_count":27,"area":"agents"},{"id":"2505.14148","title":"MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem","created":"2025-05-20","cited_by_count":25,"area":"agents"},{"id":"2602.02660","title":"MARS: Modular Agent with Reflective Search for Automated AI Research","created":"2026-02-02","cited_by_count":25,"area":"agents"},{"id":"2602.15112","title":"ResearchGym: Evaluating Language Model Agents on Real-World AI Research","created":"2026-02-16","cited_by_count":22,"area":"agents"},{"id":"2506.10974","title":"AutoMind: Adaptive Knowledgeable Agent for Automated Data Science","created":"2025-06-12","cited_by_count":20,"area":"agents"},{"id":"2512.21782","title":"Accelerating Scientific Discovery with Autonomous Goal-evolving Agents","created":"2025-12-25","cited_by_count":19,"area":"agents"},{"id":"2605.26340","title":"ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence","created":"2026-05-25","cited_by_count":19,"area":"agents"},{"id":"2606.26294","title":"The Red Queen G\\\"odel Machine: Co-Evolving Agents and Their Evaluators","created":"2026-06-24","cited_by_count":19,"area":"agents"},{"id":"2607.13104","title":"Self-Improvements in Modern Agentic Systems: A Survey","created":"2026-07-14","cited_by_count":19,"area":"agents"},{"id":"2602.07755","title":"Learning to Continually Learn via Meta-learning Agentic Memory Designs","created":"2026-02-08","cited_by_count":18,"area":"agents"},{"id":"2604.13018","title":"Toward Autonomous Long-Horizon Engineering for ML Research","created":"2026-04-14","cited_by_count":17,"area":"agents"},{"id":"2605.06651","title":"AI co-mathematician: Accelerating mathematicians with agentic AI","created":"2026-05-07","cited_by_count":17,"area":"agents"},{"id":"2601.14192","title":"Toward Efficient Agents: Memory, Tool learning, and Planning","created":"2026-01-20","cited_by_count":16,"area":"agents"},{"id":"2602.02905","title":"FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights","created":"2026-02-02","cited_by_count":16,"area":"agents"},{"id":"2605.03042","title":"ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration","created":"2026-05-04","cited_by_count":16,"area":"agents"},{"id":"2507.15550","title":"PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors","created":"2025-07-21","cited_by_count":15,"area":"agents"},{"id":"2606.03108","title":"EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning","created":"2026-06-02","cited_by_count":14,"area":"agents"},{"id":"2601.03315","title":"Why LLMs Aren't Scientists Yet: Lessons from Four Autonomous Research Attempts","created":"2026-01-06","cited_by_count":13,"area":"agents"},{"id":"2603.26499","title":"AIRA_2: Overcoming Bottlenecks in AI Research Agents","created":"2026-03-27","cited_by_count":12,"area":"agents"},{"id":"2605.30329","title":"SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?","created":"2026-05-28","cited_by_count":12,"area":"agents"},{"id":"2510.09901","title":"Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics","created":"2025-10-10","cited_by_count":11,"area":"agents"},{"id":"2510.24591","title":"ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers?","created":"2025-10-28","cited_by_count":11,"area":"agents"},{"id":"2608.20318","title":"AI4AI-Bench: Benchmarking LLM Agents in Algorithmic Design for Recursive Self-Improvement","created":"2026-08-20","cited_by_count":11,"area":"agents"},{"id":"2609.26457","title":"Recursive self-improvement of AI research agents","created":"2026-09-22","cited_by_count":11,"area":"agents"},{"id":"2506.01839","title":"Beyond Static Responses: Multi-Agent LLM Systems as a New Paradigm for Social Science Research","created":"2025-06-02","cited_by_count":10,"area":"agents"},{"id":"2608.13940","title":"AI Research Preference Models","created":"2026-08-14","cited_by_count":10,"area":"agents"},{"id":"2508.07880","title":"Multi-agent systems for chemical engineering: A review and perspective","created":"2025-08-11","cited_by_count":9,"area":"agents"},{"id":"2608.05179","title":"Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap","created":"2026-06-29","cited_by_count":9,"area":"agents"},{"id":"2506.12482","title":"Tiered Agentic Oversight: A Hierarchical Multi-Agent System for Healthcare Safety","created":"2025-06-14","cited_by_count":8,"area":"agents"},{"id":"2507.08350","title":"Exploring Design of Multi-Agent LLM Dialogues for Research Ideation","created":"2025-07-11","cited_by_count":8,"area":"agents"},{"id":"2510.06579","title":"TinyScientist: An Interactive, Extensible, and Controllable Framework for Building Research Agents","created":"2025-10-08","cited_by_count":8,"area":"agents"},{"id":"2602.04850","title":"El Agente Quntur: A research collaborator agent for quantum chemistry","created":"2026-02-04","cited_by_count":8,"area":"agents"},{"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":"2605.08956","title":"Agentic AI Scientists Are Not Built For Autonomous Scientific Discovery","created":"2026-05-09","cited_by_count":8,"area":"agents"},{"id":"2605.17373","title":"FML-bench: A Controlled Study of AI Research Agent Strategies from the Perspective of Search Dynamics","created":"2026-05-17","cited_by_count":8,"area":"agents"},{"id":"2511.02238","title":"Deep Ideation: Designing LLM Agents to Generate Novel Research Ideas on Scientific Concept Network","created":"2025-11-04","cited_by_count":7,"area":"agents"},{"id":"2511.15593","title":"What Does It Take to Be a Good AI Research Agent? Studying the Role of Ideation Diversity","created":"2025-11-19","cited_by_count":7,"area":"agents"},{"id":"2602.18710","title":"Many AI Analysts, One Dataset: Navigating the Agentic Data Science Multiverse","created":"2026-02-21","cited_by_count":7,"area":"agents"},{"id":"2604.17406","title":"EvoMaster: A Foundational Evolving Agent Framework for Agentic Science at Scale","created":"2026-04-19","cited_by_count":7,"area":"agents"},{"id":"2606.31651","title":"FARS: A Fully Automated Research System Deployed at Scale","created":"2026-06-30","cited_by_count":7,"area":"agents"},{"id":"2609.21032","title":"Scaling Discovery through Test-Time Communication","created":"2026-09-17","cited_by_count":7,"area":"agents"},{"id":"2506.22653","title":"URSA: The Universal Research and Scientific Agent","created":"2025-06-27","cited_by_count":6,"area":"agents"},{"id":"2607.12835","title":"Can LLMs Write Reliable Rubrics? A Meta-Evaluation for Experiment Reproduction","created":"2026-07-14","cited_by_count":6,"area":"agents"},{"id":"2506.20640","title":"CoMind: Towards Community-Driven Agents for Machine Learning Engineering","created":"2025-06-25","cited_by_count":5,"area":"agents"},{"id":"2510.06711","title":"Inefficiencies of Meta Agents for Agent Design","created":"2025-10-08","cited_by_count":5,"area":"agents"},{"id":"2602.18920","title":"DeepInnovator: Triggering the Innovative Capabilities of LLMs","created":"2026-02-21","cited_by_count":5,"area":"agents"},{"id":"2604.17745","title":"HiRAS: A Hierarchical Multi-Agent Framework for Paper-to-Code Generation and Execution","created":"2026-04-20","cited_by_count":5,"area":"agents"},{"id":"2605.15871","title":"Agentic Discovery of Neural Architectures: AIRA-Compose and AIRA-Design","created":"2026-05-15","cited_by_count":5,"area":"agents"},{"id":"2605.31468","title":"AutoSci: A Memory-Centric Agentic System for the Full Scientific Research Lifecycle","created":"2026-05-29","cited_by_count":5,"area":"agents"},{"id":"2609.20519","title":"SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness","created":"2026-09-17","cited_by_count":5,"area":"agents"},{"id":"2505.21471","title":"Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaboration","created":"2025-05-27","cited_by_count":4,"area":"agents"},{"id":"2509.22502","title":"InfiAgent: Self-Evolving Pyramid Agent Framework for Infinite Scenarios","created":"2025-09-26","cited_by_count":4,"area":"agents"},{"id":"2510.10472","title":"FML-bench: Benchmarking Machine Learning Agents for Scientific Research","created":"2025-10-12","cited_by_count":4,"area":"agents"},{"id":"2602.21351","title":"A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archives","created":"2026-02-24","cited_by_count":4,"area":"agents"},{"id":"2603.00214","title":"Agentic Scientific Simulation: Execution-Grounded Model Construction and Reconstruction","created":"2026-02-27","cited_by_count":4,"area":"agents"},{"id":"2603.15914","title":"The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning","created":"2026-03-16","cited_by_count":4,"area":"agents"},{"id":"2605.08941","title":"MDGYM: Benchmarking AI Agents on Molecular Simulations","created":"2026-05-09","cited_by_count":4,"area":"agents"},{"id":"2605.10813","title":"NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation","created":"2026-05-11","cited_by_count":4,"area":"agents"},{"id":"2605.13874","title":"GEAR: Genetic AutoResearch for Agentic Code Evolution","created":"2026-05-08","cited_by_count":4,"area":"agents"},{"id":"2606.01444","title":"Self-Revising Discovery Systems for Science: A Categorical Framework for Agentic Artificial Intelligence","created":"2026-05-31","cited_by_count":4,"area":"agents"},{"id":"2606.13349","title":"From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent","created":"2026-06-11","cited_by_count":4,"area":"agents"},{"id":"2608.14354","title":"ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond","created":"2026-08-14","cited_by_count":4,"area":"agents"},{"id":"2511.19423","title":"Beyond Protein Language Models: An Agentic LLM Framework for Mechanistic Enzyme Design","created":"2025-11-24","cited_by_count":3,"area":"agents"},{"id":"2512.03571","title":"EnCompass: Enhancing Agent Programming with Search Over Program Execution Paths","created":"2025-12-03","cited_by_count":3,"area":"agents"},{"id":"2603.07444","title":"HLER: Human-in-the-Loop Economic Research via Multi-Agent Pipelines for Empirical Discovery","created":"2026-03-08","cited_by_count":3,"area":"agents"},{"id":"2603.20256","title":"SciNav: A General Agent Framework for Scientific Coding Tasks","created":"2026-03-11","cited_by_count":3,"area":"agents"},{"id":"2603.23951","title":"From AI Assistant to AI Scientist: Autonomous Discovery of LLM-RL Algorithms with LLM Agents","created":"2026-03-25","cited_by_count":3,"area":"agents"},{"id":"2604.08590","title":"AlphaLab: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs","created":"2026-03-31","cited_by_count":3,"area":"agents"},{"id":"2604.16723","title":"Debate as Reward: A Multi-Agent Reward System for Scientific Ideation via RL Post-Training","created":"2026-04-17","cited_by_count":3,"area":"agents"},{"id":"2605.06607","title":"AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2605.24018","title":"EvoSci: A Bio-Inspired Multi-Agent Framework for the Evolution of Scientific Discovery","created":"2026-05-20","cited_by_count":3,"area":"agents"},{"id":"2606.07462","title":"Act As a Real Researcher: A Suite of Benchmarks Evaluating Frontier LLMs and Agentic Harnesses in Research Lifecycle","created":"2026-06-05","cited_by_count":3,"area":"agents"},{"id":"2606.13669","title":"Agents-K1: Towards Agent-native Knowledge Orchestration","created":"2026-06-11","cited_by_count":3,"area":"agents"},{"id":"2606.31229","title":"Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agents","created":"2026-06-30","cited_by_count":3,"area":"agents"},{"id":"2508.01746","title":"Bayes-Entropy Collaborative Driven Agents for Research Hypotheses Generation and Optimization","created":"2025-08-03","cited_by_count":2,"area":"agents"},{"id":"2511.04921","title":"AgentExpt: Automating AI Experiment Design with LLM-based Resource Retrieval Agent","created":"2025-11-07","cited_by_count":2,"area":"agents"},{"id":"2603.21344","title":"The AI Scientific Community: Agentic Virtual Lab Swarms","created":"2026-03-22","cited_by_count":2,"area":"agents"},{"id":"2604.09791","title":"Pioneer Agent: Continual Improvement of Small Language Models in Production","created":"2026-04-10","cited_by_count":2,"area":"agents"},{"id":"2604.22871","title":"AutoRISE: Agent-Driven Strategy Evolution for Red-Teaming Large Language Models","created":"2026-04-23","cited_by_count":2,"area":"agents"},{"id":"2605.02092","title":"NORA: A Harness-Engineered Autonomous Research Agent for End-to-End Spatial Data Science","created":"2026-05-03","cited_by_count":2,"area":"agents"},{"id":"2606.00644","title":"ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment","created":"2026-05-30","cited_by_count":2,"area":"agents"},{"id":"2606.08340","title":"Benchmarking Open-Ended Multi-Agent Coordination in Language Agents","created":"2026-06-06","cited_by_count":2,"area":"agents"},{"id":"2606.18356","title":"SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents","created":"2026-06-16","cited_by_count":2,"area":"agents"},{"id":"2606.27386","title":"Agentic Publication Protocol: An Attempt to Modernize Scientific Publication","created":"2026-06-15","cited_by_count":2,"area":"agents"}],"next_cursor":"100"}