{"total":70,"rows":[{"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":"2602.10975","title":"FeatureBench: Benchmarking Agentic Coding for Complex Feature Development","created":"2026-02-11","cited_by_count":34,"area":"agents"},{"id":"2505.20662","title":"AutoReproduce: Automatic AI Experiment Reproduction with Paper Lineage","created":"2025-05-27","cited_by_count":32,"area":null},{"id":"2505.11855","title":"When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research","created":"2025-05-17","cited_by_count":26,"area":null},{"id":"2510.05096","title":"Paper2Video: Automatic Video Generation from Scientific Papers","created":"2025-10-06","cited_by_count":24,"area":null},{"id":"2509.06917","title":"Paper2Agent: Reimagining Research Papers As Interactive and Reliable AI Agents","created":"2025-09-08","cited_by_count":23,"area":null},{"id":"2506.01372","title":"AI Scientists Fail Without Strong Implementation Capability","created":"2025-06-02","cited_by_count":21,"area":null},{"id":"2510.01290","title":"ThinKV: Thought-Adaptive KV Cache Compression for Efficient Reasoning Models","created":"2025-10-01","cited_by_count":21,"area":"lr"},{"id":"2504.20115","title":"AutoP2C: An LLM-Based Agent Framework for Code Repository Generation from Multimodal Content in Academic Papers","created":"2025-04-28","cited_by_count":20,"area":"agents"},{"id":"2509.16198","title":"RPG: A Repository Planning Graph for Unified and Scalable Codebase Generation","created":"2025-09-19","cited_by_count":19,"area":null},{"id":"2510.06056","title":"Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Research","created":"2025-10-07","cited_by_count":19,"area":null},{"id":"2506.22598","title":"RExBench: Can coding agents autonomously implement AI research extensions?","created":"2025-06-27","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":"2604.24658","title":"The Last Human-Written Paper: Agent-Native Research Artifacts","created":"2026-04-27","cited_by_count":16,"area":null},{"id":"2512.04329","title":"A Retrieval-Augmented Generation Approach to Extracting Algorithmic Logic from Neural Networks","created":"2025-12-03","cited_by_count":11,"area":"rag"},{"id":"2604.25256","title":"AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery","created":"2026-04-28","cited_by_count":11,"area":"agents"},{"id":"2605.18661","title":"AI for Auto-Research: Roadmap & User Guide","created":"2026-05-18","cited_by_count":11,"area":null},{"id":"2508.16671","title":"Reflective Paper-to-Code Reproduction Enabled by Fine-Grained Verification","created":"2025-08-21","cited_by_count":10,"area":null},{"id":"2601.12910","title":"SciCoQA: Quality Assurance for Scientific Paper--Code Alignment","created":"2026-01-19","cited_by_count":10,"area":"agents"},{"id":"2511.18734","title":"Yo'City: Personalized and Boundless 3D Realistic City Scene Generation via Self-Critic Expansion","created":"2025-11-24","cited_by_count":9,"area":null},{"id":"2605.00803","title":"Can Coding Agents Reproduce Findings in Computational Materials Science?","created":"2026-05-01","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":"2608.13331","title":"Training AI Scientists to Replicate Research","created":"2026-08-13","cited_by_count":9,"area":null},{"id":"2508.21720","title":"PosterForest: Hierarchical Multi-Agent Collaboration for Scientific Poster Generation","created":"2025-08-29","cited_by_count":8,"area":null},{"id":"2603.01801","title":"What Papers Don't Tell You: Recovering Tacit Knowledge for Automated Paper Reproduction","created":"2026-03-02","cited_by_count":6,"area":null},{"id":"2509.18487","title":"Actions Speak Louder than Prompts: A Large-Scale Study of LLMs for Graph Inference","created":"2025-09-23","cited_by_count":5,"area":null},{"id":"2511.18531","title":"LockForge: Automating Paper-to-Code for Logic Locking with Multi-Agent Reasoning LLMs","created":"2025-11-23","cited_by_count":5,"area":"agents"},{"id":"2604.21965","title":"Read the Paper, Write the Code: Agentic Reproduction of Social-Science Results","created":"2026-04-23","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":"2605.17613","title":"VeriCache: Turning Lossy KV Cache into Lossless LLM Inference","created":"2026-05-17","cited_by_count":5,"area":"inference"},{"id":"2510.24891","title":"Idea2Plan: Exploring AI-Powered Research Planning","created":"2025-10-28","cited_by_count":4,"area":null},{"id":"2603.00805","title":"NERFIFY: A Multi-Agent Framework for Turning NeRF Papers into Code","created":"2026-02-28","cited_by_count":3,"area":"agents"},{"id":"2604.14004","title":"Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents","created":"2026-04-15","cited_by_count":3,"area":"agents"},{"id":"2605.06445","title":"Constraint Decay: The Fragility of LLM Agents in Backend Code Generation","created":"2026-05-07","cited_by_count":3,"area":"agents"},{"id":"2608.19854","title":"Repo0: Design-Driven Zero-to-All Code Generation","created":"2026-08-20","cited_by_count":3,"area":"agents"},{"id":"2508.16713","title":"CelloAI: Leveraging Large Language Models for HPC Software Development in High Energy Physics","created":"2025-08-22","cited_by_count":2,"area":null},{"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":"2603.30038","title":"Benchmarking PhD-Level Coding in 3D Geometric Computer Vision","created":"2026-03-31","cited_by_count":2,"area":null},{"id":"2605.28371","title":"From paper to benchmark: agentic, framework-based reproduction of under-specified methods in machine health intelligence","created":"2026-05-27","cited_by_count":2,"area":"agents"},{"id":"2606.18237","title":"ReproRepo: Scaling Reproducibility Audits with GitHub Repository Issues","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"},{"id":"2607.02931","title":"VERITAS: Towards a General-Purpose Replication Tool for Scientific Research","created":"2026-07-03","cited_by_count":2,"area":null},{"id":"2608.04458","title":"Architectural Implications of Agentic AI Workflows","created":"2026-08-05","cited_by_count":2,"area":"agents"},{"id":"2609.00747","title":"Can Large Language Models Forecast What Researchers Study Next?","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2609.02749","title":"Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills","created":"2026-09-02","cited_by_count":2,"area":null},{"id":"2609.11117","title":"Overview of the NLPCC 2026 Shared Task 11: Agent-Based Experiment Reproduction from Scientific Papers","created":"2026-09-10","cited_by_count":2,"area":"agents"},{"id":"2509.24351","title":"From Static to Dynamic: Adaptive Monte Carlo Search for Mathematical Process Supervision","created":"2025-09-29","cited_by_count":1,"area":"lr"},{"id":"2512.02812","title":"Enhancing Automated Paper Reproduction via Prompt-Free Collaborative Agents","created":"2025-12-02","cited_by_count":1,"area":null},{"id":"2602.03849","title":"HybridQuestion: Human-AI Collaboration for Identifying High-Impact Research Questions","created":"2025-12-18","cited_by_count":1,"area":null},{"id":"2604.04324","title":"RESCORE: LLM-Driven Simulation Recovery in Control Systems Research Papers","created":"2026-04-06","cited_by_count":1,"area":null},{"id":"2605.02651","title":"ARA: Agentic Reproducibility Assessment For Scalable Support Of Scientific Peer-Review","created":"2026-05-04","cited_by_count":1,"area":"agents"},{"id":"2607.02134","title":"Coding-agents can replicate scientific machine learning papers","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2608.24252","title":"SA-Bench: Evaluating Semantic Alignment in LLM-Based Paper Reproduction","created":"2026-08-25","cited_by_count":1,"area":"agents"},{"id":"2608.24291","title":"ReproAgent: Contract-Guided Paper-to-Code Reproduction","created":"2026-08-25","cited_by_count":1,"area":null},{"id":"2508.05473","title":"Embedding Alignment in Code Generation for Audio","created":"2025-08-07","cited_by_count":0,"area":null},{"id":"2604.04089","title":"From Paper to Program: Specification-Guided Implementation of Quantum Many-Body Algorithms with Large Language Model","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2604.19606","title":"AblateCell: A Reproduce-then-Ablate Agent for Virtual Cell Repositories","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.00557","title":"Structure Liberates: How Constrained Sensemaking Produces More Novel Research Output","created":"2026-05-01","cited_by_count":0,"area":null},{"id":"2605.11154","title":"Quantifying the Reconstructability of Astrophysical Methods with Large Language Models and Information Theory: A Case Study in Spectral Reconstruction","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.16902","title":"ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.24081","title":"PixJail: Self-Evolving Paper-to-Pipeline Reproduction for Text-to-Image Jailbreak Evaluation","created":"2026-06-23","cited_by_count":0,"area":"safety"},{"id":"2607.14818","title":"Can LLMs Build a MaxSAT Solver from Papers? The CoreForge Experience","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.25199","title":"RIDGE: An Autonomous Framework for Validation and Method Discovery in LLM-Generated Option Pricing","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2609.02272","title":"PaperCompiler: Faithful Paper-to-Code Generation via Repository-Level Specification Compilation","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.19155","title":"Towards Proactive Detection of User-Side Implicit Conflicts in Human-LLM Dialogue","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2609.28850","title":"RECLAIM: Can Agents Reproduce the Claims of Machine Learning Papers?","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.35854","title":"Position: Let's Strengthen Verifiability If We Can't Enforce Reproducibility","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.38335","title":"E2E-SWE: Benchmarking LLMs on Building Working Codebases from Scratch","created":"2026-09-29","cited_by_count":0,"area":"agents"},{"id":"2610.09116","title":"SPLATIFY: Reproduce, Discover, Innovate! From Papers and Ideas to Trainable 3DGS Code","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.13361","title":"AgentSWE: Can Coding Agents Build the Agent You Actually Want?","created":"2026-10-09","cited_by_count":0,"area":"agents"}],"next_cursor":null}