{"total":18,"rows":[{"id":"2507.22358","title":"Magentic-UI: Towards Human-in-the-loop Agentic Systems","created":"2025-07-30","cited_by_count":43,"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":"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":"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":"2511.08522","title":"AlphaResearch: Accelerating New Algorithm Discovery with Language Models","created":"2025-11-11","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":"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":"2606.31651","title":"FARS: A Fully Automated Research System Deployed at Scale","created":"2026-06-30","cited_by_count":7,"area":"agents"},{"id":"2603.28807","title":"SafeClaw-R: Towards Safe and Secure Multi-Agent Personal Assistants","created":"2026-03-28","cited_by_count":6,"area":"agents"},{"id":"2603.17216","title":"ML-AutoResearch: Training Machine Learning Research Agents with Automatically Generated Environments","created":"2026-03-17","cited_by_count":2,"area":"agents"},{"id":"2608.21601","title":"K-Bench: measuring model performance on real scientific agent requests","created":"2026-08-21","cited_by_count":2,"area":"agents"},{"id":"2608.30047","title":"Can LLM Agents Discover? Evaluating Creativity on ML Engineering Tasks","created":"2026-08-30","cited_by_count":1,"area":"agents"},{"id":"2609.22104","title":"DeepInstructor: An Agentic AI Instructor for Experience-Driven Idea Evaluation","created":"2026-08-14","cited_by_count":1,"area":"agents"},{"id":"2604.01128","title":"Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers","created":"2026-04-01","cited_by_count":0,"area":"agents"},{"id":"2608.22960","title":"What Process Evaluation of Coding Agents Actually Measures: Action, Task, and Step Are Three Different Levels","created":"2026-08-24","cited_by_count":0,"area":"agents"},{"id":"2609.25804","title":"The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks","created":"2026-09-22","cited_by_count":0,"area":"agents"},{"id":"2610.01618","title":"Agents Are Systems, Not Models: Rethinking Agentic Evaluation","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.04074","title":"IdeaScientist: Orchestrating Agents for Grounded Scientific Ideation","created":"2026-10-02","cited_by_count":0,"area":"agents"}],"next_cursor":null}