{"total":94,"rows":[{"id":"2510.08558","title":"Agent Learning via Early Experience","created":"2025-10-09","cited_by_count":85,"area":null},{"id":"2503.18102","title":"AgentRxiv: Towards Collaborative Autonomous Research","created":"2025-03-23","cited_by_count":72,"area":null},{"id":"2503.21248","title":"ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition","created":"2025-03-27","cited_by_count":66,"area":null},{"id":"2503.04629","title":"SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing","created":"2025-03-06","cited_by_count":49,"area":null},{"id":"2507.15887","title":"AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2504.12976","title":"Sparks of Science: Hypothesis Generation Using Structured Paper Data","created":"2025-04-17","cited_by_count":25,"area":null},{"id":"2605.20025","title":"AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration","created":"2026-05-19","cited_by_count":25,"area":null},{"id":"2410.22394","title":"AAAR-1.0: Assessing AI's Potential to Assist Research","created":"2024-10-29","cited_by_count":24,"area":null},{"id":"2510.05096","title":"Paper2Video: Automatic Video Generation from Scientific Papers","created":"2025-10-06","cited_by_count":24,"area":null},{"id":"2606.11926","title":"Toward Generalist Autonomous Research via Hypothesis-Tree Refinement","created":"2026-06-10","cited_by_count":22,"area":null},{"id":"2411.11910","title":"AIGS: Generating Science from AI-Powered Automated Falsification","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2604.24658","title":"The Last Human-Written Paper: Agent-Native Research Artifacts","created":"2026-04-27","cited_by_count":16,"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":"2507.21184","title":"Can Language Models Discover Scaling Laws?","created":"2025-07-27","cited_by_count":13,"area":null},{"id":"2506.08140","title":"AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists","created":"2025-06-09","cited_by_count":11,"area":null},{"id":"2511.21016","title":"Gated KalmaNet: A Fading Memory Layer Through Test-Time Ridge Regression","created":"2025-11-26","cited_by_count":11,"area":null},{"id":"2605.18661","title":"AI for Auto-Research: Roadmap & User Guide","created":"2026-05-18","cited_by_count":11,"area":null},{"id":"2509.05881","title":"GeoAnalystBench: A GeoAI benchmark for assessing large language models for spatial analysis workflow and code generation","created":"2025-09-07","cited_by_count":10,"area":null},{"id":"2603.01203","title":"How Well Does Agent Development Reflect Real-World Work?","created":"2026-03-01","cited_by_count":10,"area":null},{"id":"2605.19156","title":"How Far Are We From True Auto-Research?","created":"2026-05-18","cited_by_count":10,"area":null},{"id":"2605.23204","title":"AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery","created":"2026-05-22","cited_by_count":10,"area":null},{"id":"2507.11810","title":"Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator","created":"2025-07-16","cited_by_count":9,"area":null},{"id":"2608.13331","title":"Training AI Scientists to Replicate Research","created":"2026-08-13","cited_by_count":9,"area":null},{"id":"2508.07043","title":"K-Dense Analyst: Towards Fully Automated Scientific Analysis","created":"2025-08-09","cited_by_count":6,"area":null},{"id":"2606.15932","title":"Beyond NL2Code: A Structured Survey of Multimodal Code Intelligence","created":"2026-06-14","cited_by_count":6,"area":null},{"id":"2509.20374","title":"CFDLLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics","created":"2025-09-19","cited_by_count":5,"area":null},{"id":"2510.24891","title":"Idea2Plan: Exploring AI-Powered Research Planning","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2608.17271","title":"ASI-Bench: At the Dawn of Artificial Superintelligence","created":"2026-08-18","cited_by_count":4,"area":null},{"id":"2609.19134","title":"ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments","created":"2026-09-16","cited_by_count":4,"area":null},{"id":"2512.22899","title":"HiSciBench: A Hierarchical Multi-disciplinary Benchmark for Scientific Intelligence from Reading to Discovery","created":"2025-12-28","cited_by_count":3,"area":null},{"id":"2603.20253","title":"SimulCost: A Cost-Aware Benchmark and Toolkit for Automating Physics Simulations with LLMs","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2606.23175","title":"Position: Correct Answer, Wrong Mechanism -- When AI Scientists Defend General Claims Their Own Data Contradicts","created":"2026-06-22","cited_by_count":3,"area":null},{"id":"2609.15973","title":"Discovery Foundation Models: Toward Open-Ended Discovery Intelligence","created":"2026-09-14","cited_by_count":3,"area":null},{"id":"2506.12312","title":"Perspective on Utilizing Foundation Models for Laboratory Automation in Materials Research","created":"2025-06-14","cited_by_count":2,"area":null},{"id":"2604.01206","title":"RELISH: LLM REgression with a Latent Iterative State Head","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2605.14033","title":"Sheaf-Theoretic Transport and Obstruction for Detecting Scientific Theory Shift in AI Agents","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2605.18630","title":"SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science","created":"2026-05-18","cited_by_count":2,"area":null},{"id":"2606.09774","title":"Auto-Configuring Scientific Simulators with Lightweight Coding-Agent Adapters","created":"2026-06-08","cited_by_count":2,"area":null},{"id":"2608.19072","title":"What is Missing from AI Post-Training AI: An Empirical Analysis","created":"2026-08-19","cited_by_count":2,"area":null},{"id":"2608.26701","title":"Accelerating Scientific Research with Gemini in the Real-World","created":"2026-08-27","cited_by_count":2,"area":null},{"id":"2609.01552","title":"Can LLMs Discover Scientific Laws in Real and Parallel Worlds?","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2508.18646","title":"Beyond Benchmarks: LLM Evaluation with an Anthropomorphic and Lifecycle-oriented Roadmap","created":"2025-08-26","cited_by_count":1,"area":null},{"id":"2603.01421","title":"SciDER: Scientific Data-centric End-to-end Researcher","created":"2026-03-02","cited_by_count":1,"area":null},{"id":"2604.13201","title":"InfiniteScienceGym: An Unbounded, Procedurally-Generated Benchmark for Scientific Analysis","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2604.27977","title":"D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.02351","title":"MolViBench: Evaluating LLMs on Molecular Vibe Coding","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2606.20475","title":"Marginal Advantage Accumulation for Memory-Driven Agent Self-Evolution","created":"2026-06-18","cited_by_count":1,"area":null},{"id":"2607.09025","title":"Evolutionary Intelligence for Scientific Discovery: From Evolutionary Computation to Cumulative Discovery Systems","created":"2026-07-10","cited_by_count":1,"area":null},{"id":"2607.25045","title":"CogEEGAgent: Toward Autonomous Cognitive EEG Analysis with Grounded Execution and Selection-Aware Verification","created":"2026-07-27","cited_by_count":1,"area":null},{"id":"2607.28632","title":"LLM Framework for Discovering Major Mathematical Conjectures: AI's Quest for the Next Riemann Hypothesis","created":"2026-04-19","cited_by_count":1,"area":null},{"id":"2608.11341","title":"Apodex Discovery: Reality Benchmarks and Environments for Evaluating and Building Discoverative Artificial Intelligence","created":"2026-08-11","cited_by_count":1,"area":null},{"id":"2608.12788","title":"ARAC: Benchmarking Auto-Research's Alignment and Completeness on End-to-End Researchs","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2608.13558","title":"OmniScientist: An Omni-Modal Omni-Discipline AI Scientist","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2608.24979","title":"FrontierChallenge: Evaluating Scientific Workflow Completion","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2609.09219","title":"Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents","created":"2026-09-07","cited_by_count":1,"area":null},{"id":"2512.06006","title":"Simple Agents Outperform Experts in Biomedical Imaging Workflow Optimization","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2602.12424","title":"RankLLM: Weighted Ranking of LLMs by Quantifying Question Difficulty","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2606.11176","title":"Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2607.12113","title":"Toward Trustworthy Autonomous Science: A Two-Year Community Roadmap","created":"2026-07-13","cited_by_count":0,"area":null},{"id":"2607.16038","title":"SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2607.19104","title":"SciCodePile: A 128GB Corpus and Executable Benchmark for Challenging Scientific Code Generation","created":"2026-07-21","cited_by_count":0,"area":null},{"id":"2607.25891","title":"Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2607.28098","title":"SciDataSailor: Deep Scientific Data Exploring","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.00339","title":"Bayesian and Motivated Reasoning in AI Agents","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.03569","title":"Adversarial Fast-Moving Real-World Domains as Test Beds for Benchmarking AI Scientist Capabilities","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.03600","title":"Large language models for partial differential equation workflows","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.19625","title":"Scientific Data Skills: Enabling Agent-Ready Scientific Data Services at Scale","created":"2026-08-20","cited_by_count":0,"area":null},{"id":"2608.23525","title":"EarthVerse: Benchmarking Scientific Agents Across Dynamic Earth Systems and Natural Hazards","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.28628","title":"CDEP Agent: Connecting Meteorologically Detected Temporal Compound Events to Real-World Documentary Evidence","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.28704","title":"ORDDAR: Observation-Driven Reasoning for Distortion-Resilient Decision, Action, and Cognitive Recovery","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.01982","title":"Benchmarking Language Models for Statistical Problem Formulation","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.02067","title":"ToolGate: An Executable Acceptance Pipeline for Tool-Dependent Scientific Benchmark Construction","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.07944","title":"CausalVerify: End-to-End Verification of Causal Analyses by Language Models","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.11018","title":"Defining AI Agents: A Compendium of Criteria, Metrics, and Benchmarks","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.15096","title":"OpenAI4S: Code as Action, Science as Sessions","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.22409","title":"Contextual Causality with Large Language Models: A Survey","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.28697","title":"LabFactory: Building and Evaluating Executable AI Labs","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.33012","title":"When Pair Count Is Not the Sample Size: What All-Pairs Agent Comparisons Estimate","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34469","title":"The Last Mile Is the File: OfficeEditBench for Preservation-Aware Office Editing","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36726","title":"Can AI Scientists Change Their Minds? Prior-Evidence Conflict in Synthetic Universes","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00074","title":"K-Dense BYOK: An Open-Source AI Research Assistant That Runs Locally and Keeps a Hash-Chained Lab Notebook","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2610.01819","title":"MECHVAR: Variance-Guided Mechanism Discrimination for Autonomous Machine Learning Experiment Selection","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02304","title":"SimuVerity: Benchmarking Agents for Engineering-Grade Simulink Model Generation","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.03092","title":"ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04561","title":"Recursive Improvement of a Differentiable Scientific Software Ecosystem","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.04976","title":"Priced Guidance: Can Language Models Generate Future Research Ideas?","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05140","title":"AutoSciBench: Autonomous Benchmark Generation for Evaluating Scientific Agents","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.05197","title":"From Scientific Observations to Mechanisms: Benchmarking Hypothesis Generation by AI Scientists","created":"2026-10-04","cited_by_count":0,"area":null},{"id":"2610.07614","title":"BioStudyBench: Evaluating Agents on Post-Cutoff Biomedical Studies","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.11118","title":"OpenProblemBench: Benchmarking AI on Open Problems in the Foundational Theoretical Sciences","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.11877","title":"How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.16297","title":"SLDBench v2: Active Scaling Law Discovery","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.18088","title":"ResearchFlow-Eval: Tracing the Execution Gap in End-to-End Multi-Claim Autoresearch","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.18449","title":"Autonomous Science Bench: Evaluating AI Agents for Autonomous Scientific Discovery","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}