{"total":100,"rows":[{"id":"2504.01848","title":"PaperBench: Evaluating AI's Ability to Replicate AI Research","created":"2025-04-02","cited_by_count":321,"area":null},{"id":"2410.10934","title":"Agent-as-a-Judge: Evaluate Agents with Agents","created":"2024-10-14","cited_by_count":238,"area":"agents"},{"id":"2503.16416","title":"Survey on Evaluation of LLM-based Agents","created":"2025-03-20","cited_by_count":204,"area":"agents"},{"id":"2411.15114","title":"RE-Bench: Evaluating frontier AI R&D capabilities of language model agents against human experts","created":"2024-11-22","cited_by_count":175,"area":"agents"},{"id":"2502.14499","title":"MLGym: A New Framework and Benchmark for Advancing AI Research Agents","created":"2025-02-20","cited_by_count":124,"area":"agents"},{"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":"2503.11733","title":"LLM Agents for Education: Advances and Applications","created":"2025-03-14","cited_by_count":59,"area":"agents"},{"id":"2409.07440","title":"SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories","created":"2024-09-11","cited_by_count":52,"area":"agents"},{"id":"2506.12469","title":"Levels of Autonomy for AI Agents","created":"2025-06-14","cited_by_count":48,"area":null},{"id":"2412.10999","title":"Cocoa: Co-Planning and Co-Execution with AI Agents","created":"2024-12-14","cited_by_count":39,"area":null},{"id":"2504.11524","title":"HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation","created":"2025-04-15","cited_by_count":37,"area":null},{"id":"2510.07172","title":"NewtonBench: Benchmarking Generalizable Scientific Law Discovery in LLM Agents","created":"2025-10-08","cited_by_count":36,"area":"agents"},{"id":"2504.15266","title":"Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction","created":"2025-04-21","cited_by_count":29,"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":"2503.17354","title":"HCAST: Human-Calibrated Autonomy Software Tasks","created":"2025-03-21","cited_by_count":24,"area":null},{"id":"2408.10455","title":"IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction","created":"2024-08-19","cited_by_count":22,"area":"agents"},{"id":"2410.17309","title":"Literature Meets Data: A Synergistic Approach to Hypothesis Generation","created":"2024-10-22","cited_by_count":20,"area":null},{"id":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19,"area":"agents"},{"id":"2411.11910","title":"AIGS: Generating Science from AI-Powered Automated Falsification","created":"2024-11-17","cited_by_count":18,"area":null},{"id":"2502.15224","title":"Auto-Discovery-Bench: Diagnosing Structured State Tracking in Oracle-Guided Discovery","created":"2025-02-21","cited_by_count":16,"area":null},{"id":"2502.01635","title":"The AI Agent Index","created":"2025-02-03","cited_by_count":15,"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":"2507.23276","title":"How Far Are AI Scientists from Changing the World?","created":"2025-07-31","cited_by_count":15,"area":null},{"id":"2602.12984","title":"SciAgentGym: Benchmarking Multi-Step Scientific Tool-use in LLM Agents","created":"2026-02-13","cited_by_count":15,"area":"lr"},{"id":"2502.10928","title":"Probing Semantic Routing in Large Mixture-of-Expert Models","created":"2025-02-15","cited_by_count":14,"area":"moe"},{"id":"2506.11102","title":"Evolutionary Perspectives on the Evaluation of LLM-Based AI Agents: A Comprehensive Survey","created":"2025-06-06","cited_by_count":13,"area":"agents"},{"id":"2605.18661","title":"AI for Auto-Research: Roadmap & User Guide","created":"2026-05-18","cited_by_count":11,"area":null},{"id":"2510.12088","title":"One Life to Learn: Inferring Symbolic World Models for Stochastic Environments from Unguided Exploration","created":"2025-10-14","cited_by_count":10,"area":"wm"},{"id":"2510.19788","title":"Benchmarking World-Model Learning with Environment-Level Queries","created":"2025-10-22","cited_by_count":10,"area":"wm"},{"id":"2603.01203","title":"How Well Does Agent Development Reflect Real-World Work?","created":"2026-03-01","cited_by_count":10,"area":null},{"id":"2605.26087","title":"DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking","created":"2026-05-25","cited_by_count":10,"area":"lr"},{"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":"2510.20886","title":"Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People","created":"2025-10-23","cited_by_count":9,"area":"agents"},{"id":"2412.06438","title":"Can foundation models actively gather information in interactive environments to test hypotheses?","created":"2024-12-09","cited_by_count":8,"area":null},{"id":"2412.16270","title":"MetaScientist: A Human-AI Synergistic Framework for Automated Mechanical Metamaterial Design","created":"2024-12-20","cited_by_count":8,"area":null},{"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":"2604.09554","title":"LABBench2: An Improved Benchmark for AI Systems Performing Biology Research","created":"2026-02-04","cited_by_count":8,"area":null},{"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":"2608.14905","title":"How Do Agents Fail on AutoResearch: End-to-End Diagnostic Evaluation on 100 Real-World Frontier Research Tasks","created":"2026-08-14","cited_by_count":8,"area":"agents"},{"id":"2606.05684","title":"AdaMEM: Test-Time Adaptive Memory for Language Agents","created":"2026-06-04","cited_by_count":6,"area":"agents"},{"id":"2608.25286","title":"BixBench3: Benchmarking AI agents on research-study-scale computational biology tasks","created":"2026-08-26","cited_by_count":5,"area":"agents"},{"id":"2505.24302","title":"ScienceMeter: Tracking Scientific Knowledge Updates in Language Models","created":"2025-05-30","cited_by_count":4,"area":null},{"id":"2506.08800","title":"Measuring Data Science Automation: A Survey of Evaluation Tools for AI Assistants and Agents","created":"2025-06-10","cited_by_count":4,"area":"agents"},{"id":"2605.26029","title":"CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists","created":"2026-05-25","cited_by_count":4,"area":"agents"},{"id":"2605.30690","title":"ElasticMem: Latent Memory as a Learnable Resource for LLM Agents","created":"2026-05-29","cited_by_count":4,"area":"agents"},{"id":"2606.01961","title":"AutoMedBench: Towards Medical AutoResearch with Agentic AI Models","created":"2026-06-01","cited_by_count":4,"area":"agents"},{"id":"2608.17271","title":"ASI-Bench: At the Dawn of Artificial Superintelligence","created":"2026-08-18","cited_by_count":4,"area":null},{"id":"2608.26081","title":"SwarmWorld: Stigmergic technological evolution in societies of language-model agents","created":"2026-08-26","cited_by_count":4,"area":"agents"},{"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":"2509.14778","title":"OpenLens AI: Fully Autonomous Research Agent for Health Infomatics","created":"2025-09-18","cited_by_count":3,"area":"agents"},{"id":"2512.17838","title":"ReX-MLE: The Autonomous Agent Benchmark for Medical Imaging Challenges","created":"2025-12-19","cited_by_count":3,"area":"agents"},{"id":"2604.06111","title":"AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2604.17609","title":"Agents Explore but Agents Ignore: LLMs Lack Environmental Curiosity","created":"2026-04-19","cited_by_count":3,"area":"agents"},{"id":"2604.28031","title":"Models Recall What They Violate: Constraint Adherence in Multi-Turn LLM Ideation","created":"2026-04-30","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":"2607.28990","title":"Scaling Scientific Discovery Environments for Turn-Level Agentic RL","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2608.12593","title":"DiG-bench: Discovery in Games","created":"2026-08-12","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":"2510.17491","title":"Empowering Real-World: A Survey on the Technology, Practice, and Evaluation of LLM-driven Industry Agents","created":"2025-10-20","cited_by_count":2,"area":"lr"},{"id":"2605.04922","title":"Evolving Idea Graphs with Learnable Edits-and-Commits for Multi-Agent Scientific Ideation","created":"2026-05-06","cited_by_count":2,"area":"agents"},{"id":"2605.12178","title":"Do Enterprise Systems Need Learned World Models? The Importance of Context to Infer Dynamics","created":"2026-05-12","cited_by_count":2,"area":"wm"},{"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":"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":"2506.21329","title":"Active Inference AI Systems for Scientific Discovery","created":"2025-06-26","cited_by_count":1,"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":"2510.01531","title":"Information Seeking for Robust Decision Making under Partial Observability","created":"2025-10-02","cited_by_count":1,"area":null},{"id":"2511.15830","title":"Mini Amusement Parks (MAPs): A Testbed for Modelling Business Decisions","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2512.08139","title":"Robust Agents in Open-Ended Worlds","created":"2025-12-09","cited_by_count":1,"area":"agents"},{"id":"2604.24697","title":"Can Current Agents Close the Discovery-to-Application Gap? A Case Study in Minecraft","created":"2026-04-27","cited_by_count":1,"area":"agents"},{"id":"2606.16802","title":"LabOSBench: Benchmarking Computer Use Agents for Scientific Instrument Control","created":"2026-06-15","cited_by_count":1,"area":"agents"},{"id":"2606.22610","title":"PaperClaw: Harnessing Agents for Autonomous Research and Human-in-the-Loop Refinement","created":"2026-06-21","cited_by_count":1,"area":"agents"},{"id":"2608.04738","title":"EviGraph: Evidence-Guided Autonomous Research Agents","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2609.05079","title":"TruthInsightBench: An Evidence-Grounded Benchmark for Automated Evaluation of Open-Ended Scientific Discovery Agents","created":"2026-09-04","cited_by_count":1,"area":"agents"},{"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":"2609.35750","title":"KV-streams for Efficient Compaction in Agentic Reinforcement Learning","created":"2026-09-28","cited_by_count":1,"area":"agents"},{"id":"2503.10469","title":"Deep Learning based discovery of Integrable Systems","created":"2025-03-13","cited_by_count":0,"area":null},{"id":"2506.11065","title":"Smotrom tvoja pa ander drogoj verden! Resurrecting Dead Pidgin with Generative Models: Russenorsk Case Study","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2605.03308","title":"Revisiting the Travel Planning Capabilities of Large Language Models","created":"2026-05-05","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":"2607.16038","title":"SciForge: An AI-Native, Multimodal Workbench for Scientific Discovery","created":"2026-07-17","cited_by_count":0,"area":null},{"id":"2608.10792","title":"ChemWorld: Programmable Chemical Worlds for Controlled and Replayable Agent Experimentation","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2608.26086","title":"TraceML: An Empirical Analysis of Human-Agent Planning in Machine Learning Development","created":"2026-08-26","cited_by_count":0,"area":"agents"},{"id":"2609.27490","title":"WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.30199","title":"ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.00492","title":"EurekaBench: Measuring Agentic Ability to Discover New Scientific Insights","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.00511","title":"Before Agents Decide: Epistemic Action in LLM-Based Systems","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.00854","title":"Are Frontier VLM Agents Ready to Be Robot Generalists? An Empirical Study with the Embodied Agent Arena","created":"2026-10-01","cited_by_count":0,"area":"mllm"},{"id":"2610.02588","title":"Open-Endedness Bench: Measuring Epistemic Process from Agent Records","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.03092","title":"ULTRADISCOVERY: Abductive Exploration in an Interconnected, Epistemically Open Universe","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.07620","title":"Explore, Then Commit: Measurement-Efficient Scientific Law Discovery with Language Models","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.12789","title":"EvoBelief: Falsifiable World Models for Self-Improving LLM Agents","created":"2026-10-08","cited_by_count":0,"area":"wm"},{"id":"2610.14381","title":"ACED-Bench: Evaluating How LLM Agents Acquire and Act on Causal Evidence","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.16867","title":"Davinci-Tool: Scaling Agentic Tool-Use Supervision with Verifiable Executable Environments","created":"2026-10-12","cited_by_count":0,"area":"agents"},{"id":"2610.17874","title":"Searching for What Matters: Open-Ended Discovery of Multiple Hypotheses with Agentic Data Exploration","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.18449","title":"Autonomous Science Bench: Evaluating AI Agents for Autonomous Scientific Discovery","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.20012","title":"ChemArgus: Automated Scientific Diagnostics for Lab-Grade Multimodal Chemistry Reasoning: A Frontier Benchmark","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}