{"total":97,"rows":[{"id":"2501.04227","title":"Agent Laboratory: Using LLM Agents as Research Assistants","created":"2025-01-08","cited_by_count":425,"area":"agents"},{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"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":"2505.18705","title":"AI-Researcher: Autonomous Scientific Innovation","created":"2025-05-24","cited_by_count":100,"area":"lr"},{"id":"2503.24047","title":"Towards Scientific Intelligence: A Survey of LLM-based Scientific Agents","created":"2025-03-31","cited_by_count":98,"area":"agents"},{"id":"2505.13259","title":"From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery","created":"2025-05-19","cited_by_count":93,"area":null},{"id":"2503.18102","title":"AgentRxiv: Towards Collaborative Autonomous Research","created":"2025-03-23","cited_by_count":72,"area":null},{"id":"2504.17192","title":"Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning","created":"2025-04-24","cited_by_count":70,"area":null},{"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":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"id":"2502.05151","title":"Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation","created":"2025-02-07","cited_by_count":42,"area":"mllm"},{"id":"2502.14297","title":"Evaluating Sakana's AI Scientist: Bold Claims, Mixed Results, and a Promising Future?","created":"2025-02-20","cited_by_count":32,"area":null},{"id":"2503.08506","title":"ReviewAgents: Bridging the Gap Between Human and AI-Generated Paper Reviews","created":"2025-03-11","cited_by_count":32,"area":null},{"id":"2505.20662","title":"AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage","created":"2025-05-27","cited_by_count":32,"area":null},{"id":"2506.17335","title":"LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research","created":"2025-06-19","cited_by_count":29,"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":"2501.03916","title":"Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedback","created":"2025-01-07","cited_by_count":25,"area":"lr"},{"id":"2509.01396","title":"DeepResearch Arena: The First Exam of LLMs' Research Abilities via Seminar-Grounded Tasks","created":"2025-09-01","cited_by_count":24,"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":"2506.01372","title":"AI Scientists Fail Without Strong Implementation Capability","created":"2025-06-02","cited_by_count":21,"area":null},{"id":"2504.16728","title":"IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery","created":"2025-04-23","cited_by_count":19,"area":null},{"id":"2506.22026","title":"Literature-Grounded Novelty Assessment of Scientific Ideas","created":"2025-06-27","cited_by_count":19,"area":null},{"id":"2502.16487","title":"All That Glitters is Not Novel: Plagiarism in AI Generated Research","created":"2025-02-23","cited_by_count":18,"area":null},{"id":"2507.23276","title":"How Far Are AI Scientists from Changing the World?","created":"2025-07-31","cited_by_count":15,"area":null},{"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":"2508.10795","title":"Beyond \"Not Novel Enough\": Enriching Scholarly Critique with LLM-Assisted Feedback","created":"2025-08-14","cited_by_count":12,"area":null},{"id":"2506.00249","title":"MIR: Methodology Inspiration Retrieval for Scientific Research Problems","created":"2025-05-30","cited_by_count":11,"area":"lr"},{"id":"2605.18661","title":"AI for Auto-Research: Roadmap & User Guide","created":"2026-05-18","cited_by_count":11,"area":null},{"id":"2506.12937","title":"HypER: Literature-grounded Hypothesis Generation and Distillation with Provenance","created":"2025-06-15","cited_by_count":10,"area":"lr"},{"id":"2603.10303","title":"Is this Idea Novel? An Automated Benchmark for Judgment of Research Ideas","created":"2026-03-11","cited_by_count":10,"area":null},{"id":"2505.14599","title":"Toward Reliable Scientific Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models","created":"2025-05-20","cited_by_count":9,"area":null},{"id":"2510.12367","title":"LLM-REVal: Can We Trust LLM Reviewers Yet?","created":"2025-10-14","cited_by_count":9,"area":null},{"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":"2503.01424","title":"From Hypothesis to Publication: A Comprehensive Survey of AI-Driven Research Support Systems","created":"2025-03-03","cited_by_count":8,"area":null},{"id":"2507.21035","title":"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis","created":"2025-07-28","cited_by_count":8,"area":"agents"},{"id":"2508.21720","title":"PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation","created":"2025-08-29","cited_by_count":8,"area":null},{"id":"2602.14367","title":"InnoEval: On Research Idea Evaluation as a Knowledge-Grounded, Multi-Perspective Reasoning Problem","created":"2026-02-16","cited_by_count":8,"area":"lr"},{"id":"2603.27146","title":"Learning to Predict Future-Aligned Research Proposals with Language Models","created":"2026-03-28","cited_by_count":8,"area":null},{"id":"2604.09793","title":"GIANTS: Generative Insight Anticipation from Scientific Literature","created":"2026-04-10","cited_by_count":8,"area":null},{"id":"2505.11336","title":"XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration","created":"2025-05-16","cited_by_count":7,"area":null},{"id":"2503.08549","title":"GoAI: Enhancing AI Students' Learning Paths and Idea Generation via Graph of AI Ideas","created":"2025-03-11","cited_by_count":6,"area":null},{"id":"2604.28158","title":"Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists","created":"2026-04-30","cited_by_count":6,"area":null},{"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":"2505.19806","title":"Exploring Consciousness in LLMs: A Systematic Survey of Theories, Implementations, and Frontier Risks","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2508.14317","title":"SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writing","created":"2025-08-20","cited_by_count":5,"area":null},{"id":"2509.21978","title":"MotivGraph-SoIQ: Integrating Motivational Knowledge Graphs and Socratic Dialogue for Enhanced LLM Ideation","created":"2025-09-26","cited_by_count":5,"area":null},{"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":"2502.12929","title":"Flow-of-Options: Diversified and Improved LLM Reasoning by Thinking Through Options","created":"2025-02-18","cited_by_count":3,"area":"lr"},{"id":"2505.21396","title":"Augmenting Research Ideation with Data: An Empirical Investigation in Social Science","created":"2025-05-27","cited_by_count":3,"area":null},{"id":"2507.01717","title":"Agent Ideate: A Framework for Product Idea Generation from Patents Using Agentic AI","created":"2025-07-02","cited_by_count":3,"area":"agents"},{"id":"2510.27251","title":"FinPos: A Position-Aware Trading Agent System for Real Financial Markets","created":"2025-10-31","cited_by_count":3,"area":"agents"},{"id":"2601.19916","title":"PaperAudit-Bench: Benchmarking Error Detection in Research Papers for Critical Automated Peer Review","created":"2026-01-07","cited_by_count":3,"area":null},{"id":"2603.14575","title":"CausalEvolve: Towards Open-Ended Discovery with Causal Scratchpad","created":"2026-03-15","cited_by_count":3,"area":null},{"id":"2603.29557","title":"FlowPIE: Test-Time Scientific Idea Evolution with Flow-Guided Literature Exploration","created":"2026-03-31","cited_by_count":3,"area":null},{"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":"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":"2506.16010","title":"SimuPanel: A Novel Immersive Multi-Agent System to Simulate Interactive Expert Panel Discussion","created":"2025-06-19","cited_by_count":2,"area":"agents"},{"id":"2508.12257","title":"Structuring the Unstructured: A Systematic Review of Text-to-Structure Generation for Agentic AI with a Universal Evaluation Framework","created":"2025-08-17","cited_by_count":2,"area":"agents"},{"id":"2511.16997","title":"MirrorMind: Empowering OmniScientist with the Expert Perspectives and Collective Knowledge of Human Scientists","created":"2025-11-21","cited_by_count":2,"area":null},{"id":"2602.07943","title":"IV Co-Scientist: Multi-Agent LLM Framework for Causal Instrumental Variable Discovery","created":"2026-02-08","cited_by_count":2,"area":"agents"},{"id":"2605.21491","title":"Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation","created":"2026-04-06","cited_by_count":2,"area":null},{"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":"2606.09105","title":"Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured Contexts","created":"2026-06-08","cited_by_count":2,"area":"rag"},{"id":"2608.13136","title":"LigBench: A Unified and Human-Aligned Benchmark for LLM-based Research Idea Generation","created":"2026-08-13","cited_by_count":2,"area":null},{"id":"2503.18865","title":"Structuring Scientific Innovation: A Framework for Modeling and Discovering Impactful Knowledge Combinations","created":"2025-03-24","cited_by_count":1,"area":null},{"id":"2507.10522","title":"DeepResearch$^{\\text{Eco}}$: A Recursive Agentic Workflow for Complex Scientific Question Answering in Ecology","created":"2025-07-14","cited_by_count":1,"area":"agents"},{"id":"2601.12473","title":"Capability-Aware Early-Stage Research Idea Evaluation","created":"2026-01-18","cited_by_count":1,"area":null},{"id":"2604.15145","title":"An Axiomatic Benchmark for Evaluation of Scientific Novelty Metrics","created":"2026-04-16","cited_by_count":1,"area":null},{"id":"2605.22878","title":"SciAtlas: A Computable Atlas of Science for Knowledge-Grounded AI Research","created":"2026-05-20","cited_by_count":1,"area":null},{"id":"2605.30961","title":"EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation","created":"2026-05-29","cited_by_count":1,"area":null},{"id":"2607.22375","title":"IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation","created":"2026-07-24","cited_by_count":1,"area":"agents"},{"id":"2607.28631","title":"Can AI Evaluate AI Scientists? A Benchmarking Study of Autonomous Research Generation Systems Using Automated Multi-Model Review","created":"2026-04-18","cited_by_count":1,"area":null},{"id":"2608.08958","title":"Idea Search: Guiding Tree Search with Ideas to Explore Diverse Scientific Methods","created":"2026-08-09","cited_by_count":1,"area":"lr"},{"id":"2608.10740","title":"Tree-of-Ideas: Automated Research Ideation via Cross-Trajectory Reasoning over Scholarly Evolution","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2608.16645","title":"Reconstruction: A Blind Benchmark for Recovering Research Ideas from Pre-Publication Bibliographies","created":"2026-08-17","cited_by_count":1,"area":null},{"id":"2610.11966","title":"MindFlow: Mind Supernet Powered Thinking Flows for Research Idea Innovation","created":"2026-10-08","cited_by_count":1,"area":"lr"},{"id":"2510.21341","title":"Magellan: Guided MCTS for Latent Space Exploration and Novelty Generation","created":"2025-10-24","cited_by_count":0,"area":null},{"id":"2601.18998","title":"Malicious Repurposing of Open Science Artefacts by Using Large Language Models","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2602.22215","title":"Graph Your Way to Inspiration: Integrating Co-Author Graphs with Retrieval-Augmented Generation for Large Language Model Based Scientific Idea Generation","created":"2025-12-05","cited_by_count":0,"area":"rag"},{"id":"2603.15952","title":"Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents","created":"2026-03-16","cited_by_count":0,"area":"lr"},{"id":"2604.12243","title":"Continuous Knowledge Metabolism: Generating Scientific Hypotheses from Evolving Literature","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.06345","title":"More Than Can Be Said: A Benchmark and Framework for Pre-Question Scientific Ideation","created":"2026-05-07","cited_by_count":0,"area":"agents"},{"id":"2605.15011","title":"The Scientific Contribution Graph: Automated Literature-based Technological Roadmapping at Scale","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2606.05443","title":"MIRAI: Prediction and Generation of High-Impact Academic Research","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.29630","title":"SFBench: The SciFy Scientific Feasibility Benchmark","created":"2026-06-28","cited_by_count":0,"area":null},{"id":"2607.08758","title":"Ideas Have Genomes: Benchmarking Scientific Lineage Reasoning and Lineage-Grounded Idea Generation","created":"2026-07-09","cited_by_count":0,"area":"lr"},{"id":"2607.14118","title":"Budgeted Subset Refinement for Execution-Aware LLM Research Ideation","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2608.03138","title":"Internalizing Academic Writing Workflows for Introduction Generation via Struct-Aware Policy Learning","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.20361","title":"Toward Auto-Research: Mining Falsifiable Research Ideas from Paper Knowledge Graphs with Categorical Structure","created":"2026-06-17","cited_by_count":0,"area":null},{"id":"2608.20960","title":"Can Scientific Claims Be Removed from Large Language Models? A Systematic Evaluation of Claim-Level Unlearning","created":"2026-08-21","cited_by_count":0,"area":"safety"},{"id":"2608.25660","title":"Think-Probe-Respond: Improving Large Language Models as Judges of Research Idea Novelty","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2609.07611","title":"AgentIdeaBench: Benchmarking Scientific Ideation in the Agent Era","created":"2026-09-07","cited_by_count":0,"area":"agents"},{"id":"2609.10092","title":"RAP: Research Attention Prediction Reveals Target-Conditioned Evidence Acquisition Biases","created":"2026-09-09","cited_by_count":0,"area":"agents"},{"id":"2609.23735","title":"ScholarStack: Layered Research Asset Orchestration and Cross-Task Reuse for Scientific Agents","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2610.02022","title":"Old Ideas, Novel Problems: The Instability of LLM-Based Novelty Evaluation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.04074","title":"IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.04339","title":"ShadowMiner v1 - An Experience Report on Implementing and Measuring a Problem-and-Hypothesis Discovery Engine","created":"2026-10-03","cited_by_count":0,"area":null}],"next_cursor":null}