{"total":156,"rows":[{"id":"2510.11967","title":"Scaling Long-Horizon LLM Agent via Context-Folding","created":"2025-10-13","cited_by_count":148,"area":"agents"},{"id":"2510.00615","title":"ACON: Optimizing Context Compression for Long-horizon LLM Agents","created":"2025-10-01","cited_by_count":136,"area":"agents"},{"id":"2506.13651","title":"xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluations","created":"2025-06-16","cited_by_count":120,"area":null},{"id":"2507.09089","title":"Measuring the Impact of Early-2025 AI on Experienced Open-Source Developer Productivity","created":"2025-07-12","cited_by_count":101,"area":null},{"id":"2511.02824","title":"Kosmos: An AI Scientist for Autonomous Discovery","created":"2025-11-04","cited_by_count":92,"area":"wm"},{"id":"2606.29537","title":"OSWorld 2.0: Benchmarking Computer Use Agents on Long-Horizon Real-World Tasks","created":"2026-06-28","cited_by_count":40,"area":"agents"},{"id":"2604.14228","title":"Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems","created":"2026-04-14","cited_by_count":38,"area":"agents"},{"id":"2512.00193","title":"A Rosetta Stone for AI Benchmarks","created":"2025-11-28","cited_by_count":36,"area":null},{"id":"2507.01786","title":"Probing and Steering Evaluation Awareness of Language Models","created":"2025-07-02","cited_by_count":35,"area":null},{"id":"2508.19461","title":"Reliable Weak-to-Strong Monitoring of LLM Agents","created":"2025-08-26","cited_by_count":31,"area":"agents"},{"id":"2504.21848","title":"Characterizing AI Agents for Alignment and Governance","created":"2025-04-30","cited_by_count":30,"area":null},{"id":"2506.14852","title":"Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents","created":"2025-06-17","cited_by_count":27,"area":"agents"},{"id":"2507.20526","title":"Security Challenges in AI Agent Deployment: Insights from a Large Scale Public Competition","created":"2025-07-28","cited_by_count":24,"area":"lr"},{"id":"2509.14260","title":"Incomplete Tasks Induce Shutdown Resistance in Some Frontier LLMs","created":"2025-09-13","cited_by_count":22,"area":null},{"id":"2604.24964","title":"Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks","created":"2026-04-27","cited_by_count":21,"area":"agents"},{"id":"2504.05259","title":"How to evaluate control measures for LLM agents? A trajectory from today to superintelligence","created":"2025-04-07","cited_by_count":20,"area":"agents"},{"id":"2512.14895","title":"Imitation Learning for Multi-turn LM Agents via On-policy Expert Corrections","created":"2025-12-16","cited_by_count":19,"area":"agents"},{"id":"2608.05466","title":"Recursive Synthesis for Long-Horizon Terminal Tasks","created":"2026-08-05","cited_by_count":19,"area":null},{"id":"2505.05602","title":"HiBayES: A Hierarchical Bayesian Modeling Framework for AI Evaluation Statistics","created":"2025-05-08","cited_by_count":18,"area":null},{"id":"2603.05344","title":"Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learned","created":"2026-03-05","cited_by_count":18,"area":"agents"},{"id":"2510.10304","title":"Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting","created":"2025-10-11","cited_by_count":13,"area":"agents"},{"id":"2512.09187","title":"WOLF: Werewolf-based Observations for LLM Deception and Falsehoods","created":"2025-12-09","cited_by_count":13,"area":null},{"id":"2608.01964","title":"LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks","created":"2026-08-03","cited_by_count":13,"area":"agents"},{"id":"2606.07157","title":"Think Fast: Estimating No-CoT Task-Completion Time Horizons of Frontier AI Models","created":"2026-06-05","cited_by_count":12,"area":"lr"},{"id":"2510.24591","title":"ReplicationBench: Can AI Agents Replicate Astrophysics Research Papers?","created":"2025-10-28","cited_by_count":11,"area":"agents"},{"id":"2604.00594","title":"Agent psychometrics: Task-level performance prediction in agentic coding benchmarks","created":"2026-04-01","cited_by_count":11,"area":"agents"},{"id":"2601.23045","title":"The Hot Mess of AI: How Does Misalignment Scale With Model Intelligence and Task Complexity?","created":"2026-01-30","cited_by_count":10,"area":null},{"id":"2605.13625","title":"How to Interpret Agent Behavior","created":"2026-05-13","cited_by_count":10,"area":null},{"id":"2605.29548","title":"Why Larger Models Learn More: Effects of Capacity, Interference, and Rare-Task Retention","created":"2026-05-28","cited_by_count":10,"area":null},{"id":"2510.07312","title":"h1: Bootstrapping LLMs to Reason over Longer Horizons via Reinforcement Learning","created":"2025-10-08","cited_by_count":9,"area":"lr"},{"id":"2601.20613","title":"AgentIF-OneDay: A Task-level Instruction-Following Benchmark for General AI Agents in Daily Scenarios","created":"2026-01-28","cited_by_count":9,"area":"agents"},{"id":"2602.06948","title":"Agentic Uncertainty Reveals Agentic Overconfidence","created":"2026-02-06","cited_by_count":9,"area":"agents"},{"id":"2608.18580","title":"FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis","created":"2026-08-19","cited_by_count":9,"area":null},{"id":"2506.06414","title":"Benchmarking Misuse Mitigation Against Covert Adversaries","created":"2025-06-06","cited_by_count":8,"area":null},{"id":"2508.04586","title":"Position: The Current AI Conference Model is Unsustainable! Diagnosing the Crisis of Centralized AI Conference","created":"2025-08-06","cited_by_count":8,"area":null},{"id":"2510.02557","title":"Orchestrating Human-AI Teams: The Manager Agent as a Unifying Research Challenge","created":"2025-10-02","cited_by_count":8,"area":"agents"},{"id":"2510.06824","title":"Efficient numeracy in language models through single-token number embeddings","created":"2025-10-08","cited_by_count":7,"area":null},{"id":"2511.15593","title":"What Does It Take to Be a Good AI Research Agent? Studying the Role of Ideation Diversity","created":"2025-11-19","cited_by_count":7,"area":"agents"},{"id":"2604.21098","title":"Propensity Inference: Environmental Contributors to LLM Behaviour","created":"2026-04-22","cited_by_count":7,"area":null},{"id":"2608.02657","title":"Your Agentic LLMs Secretly Encode Indirect Prompt-Injection Exposure in Hidden States","created":"2026-08-01","cited_by_count":7,"area":"agents"},{"id":"2608.19652","title":"Can Agent Memory Systems Track Evolving State?","created":"2026-08-20","cited_by_count":7,"area":"agents"},{"id":"2506.04098","title":"TextAtari: 100K Frames Game Playing with Language Agents","created":"2025-06-04","cited_by_count":6,"area":"agents"},{"id":"2602.04930","title":"Attack Selection Reduces Safety in Concentrated AI Control Settings against Trusted Monitoring","created":"2026-02-04","cited_by_count":6,"area":"safety"},{"id":"2602.07267","title":"BRIDGE: Predicting Human Task Completion Time From Model Performance","created":"2026-02-06","cited_by_count":6,"area":null},{"id":"2605.16626","title":"SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors","created":"2026-05-15","cited_by_count":6,"area":"agents"},{"id":"2505.19915","title":"Evaluating AI cyber capabilities with crowdsourced elicitation","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2506.00172","title":"Breakpoint: Scalable evaluation of system-level reasoning in LLM code agents","created":"2025-05-30","cited_by_count":5,"area":"lr"},{"id":"2507.12872","title":"Manipulation Attacks by Misaligned AI: Risk Analysis and Safety Case Framework","created":"2025-07-17","cited_by_count":5,"area":null},{"id":"2507.15759","title":"Interaction as Intelligence: Deep Research With Human-AI Partnership","created":"2025-07-21","cited_by_count":5,"area":null},{"id":"2509.22170","title":"Leveraging LLM Agents for Automated Video Game Testing","created":"2025-09-26","cited_by_count":5,"area":"agents"},{"id":"2606.08529","title":"Scaffold Effects on GAIA: A Controlled Comparison","created":"2026-06-07","cited_by_count":5,"area":null},{"id":"2504.05755","title":"Unraveling Human-AI Teaming: A Review and Outlook","created":"2025-04-08","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":"2511.01348","title":"The Future of Generative AI in Software Engineering: A Vision from Industry and Academia in the European GENIUS Project","created":"2025-11-03","cited_by_count":4,"area":null},{"id":"2601.20886","title":"IDE-Bench: Evaluating Large Language Models as IDE Agents on Real-World Software Engineering Tasks","created":"2026-01-28","cited_by_count":4,"area":null},{"id":"2602.04577","title":"Semantic Self-Distillation for Language Model Uncertainty","created":"2026-02-04","cited_by_count":4,"area":"distill"},{"id":"2605.20520","title":"Open-World Evaluations for Measuring Frontier AI Capabilities","created":"2026-05-19","cited_by_count":4,"area":null},{"id":"2605.30169","title":"Dissociative Identity: Language Model Agents Lack Grounding for Reputation Mechanisms","created":"2026-05-28","cited_by_count":4,"area":"agents"},{"id":"2606.12683","title":"From AGI to ASI","created":"2026-06-10","cited_by_count":4,"area":null},{"id":"2508.19988","title":"AgentCoMa: A Compositional Benchmark Mixing Commonsense and Mathematical Reasoning in Real-World Scenarios","created":"2025-08-27","cited_by_count":3,"area":"lr"},{"id":"2511.19492","title":"Forecasting AI Time Horizon Under Compute Slowdowns","created":"2025-11-23","cited_by_count":3,"area":null},{"id":"2512.00742","title":"On the Regulatory Potential of User Interfaces for AI Agent Governance","created":"2025-11-30","cited_by_count":3,"area":null},{"id":"2601.23211","title":"Multi-Agent Systems Should be Treated as Principal-Agent Problems","created":"2026-01-30","cited_by_count":3,"area":"agents"},{"id":"2602.10153","title":"Basic Legibility Protocols Improve Trusted Monitoring","created":"2026-02-09","cited_by_count":3,"area":"safety"},{"id":"2604.00010","title":"Can LLMs Perceive Time? An Empirical Investigation","created":"2026-03-09","cited_by_count":3,"area":null},{"id":"2606.00579","title":"Sandboxed Coding Agents are Competitive Omni-modal Task Solvers","created":"2026-05-30","cited_by_count":3,"area":"mllm"},{"id":"2606.05342","title":"SentinelBench: A Benchmark for Long-Running Monitoring Agents","created":"2026-06-03","cited_by_count":3,"area":null},{"id":"2505.02709","title":"Technical Report: Evaluating Goal Drift in Language Model Agents","created":"2025-05-05","cited_by_count":2,"area":"agents"},{"id":"2507.21839","title":"Against racing to AGI: Cooperation, deterrence, and catastrophic risks","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2508.15858","title":"Building and Measuring Trust between Large Language Models","created":"2025-08-20","cited_by_count":2,"area":null},{"id":"2511.00180","title":"ParaScopes: What do Language Models Activations Encode About Future Text?","created":"2025-10-31","cited_by_count":2,"area":null},{"id":"2512.21127","title":"A Real-World Evaluation of LLM Medication Safety Reviews in NHS Primary Care","created":"2025-12-24","cited_by_count":2,"area":null},{"id":"2605.12233","title":"No More, No Less: Task Alignment in Terminal Agents","created":"2026-05-12","cited_by_count":2,"area":null},{"id":"2605.12366","title":"Classifier Context Rot: Monitor Performance Degrades with Context Length","created":"2026-05-12","cited_by_count":2,"area":"agents"},{"id":"2605.15164","title":"Position: Behavioural Assurance Cannot Verify the Safety Claims Governance Now Demands","created":"2026-05-14","cited_by_count":2,"area":null},{"id":"2607.01087","title":"Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering","created":"2026-07-01","cited_by_count":2,"area":"agents"},{"id":"2607.08066","title":"Persuasion Attacks Can Decrease Effectiveness of CoT Monitoring","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2607.19321","title":"ResearchArena: Evaluating Sabotage and Monitoring in Automated AI R&D","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2608.00355","title":"CurveShift: Is Agent Progress Scalar? Separating Level from Shape","created":"2026-07-31","cited_by_count":2,"area":"agents"},{"id":"2609.01595","title":"Mechanism Design for Alignment and Control","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2506.00047","title":"Risks of AI-driven product development and strategies for their mitigation","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2507.06398","title":"Jolting Technologies: Superexponential Acceleration in AI Capabilities and Implications for AGI","created":"2025-07-08","cited_by_count":1,"area":null},{"id":"2509.22735","title":"Regulating the Agency of LLM-based Agents","created":"2025-09-25","cited_by_count":1,"area":"agents"},{"id":"2602.04836","title":"Are AI Capabilities Increasing Exponentially? A Competing Hypothesis","created":"2026-02-04","cited_by_count":1,"area":null},{"id":"2604.01363","title":"Crashing Waves vs. Rising Tides: Findings on AI Automation from Thousands of Worker Evaluations of Labor Market Tasks","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2605.12131","title":"Rollout Cards: A Reproducibility Standard for Agent Research","created":"2026-05-12","cited_by_count":1,"area":"lr"},{"id":"2605.18380","title":"QSTRBench: a New Benchmark to Evaluate the Ability of Language Models to Reason with Qualitative Spatial and Temporal Calculi","created":"2026-05-18","cited_by_count":1,"area":"lr"},{"id":"2605.30628","title":"The Architecture of Errors: From Universal Impossibility to Patch-Local LLM Reliability","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2606.13763","title":"Do programming languages still matter to your AI coding agent teammate? Evidence at scale from chess engines","created":"2026-06-11","cited_by_count":1,"area":"agents"},{"id":"2606.13892","title":"Crypto x AI, AI x Crypto: A Survey","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.19613","title":"StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns","created":"2026-06-17","cited_by_count":1,"area":"agents"},{"id":"2606.27416","title":"Glite ARF: Verifier-Driven Research with Parallel LLM Coding Agents","created":"2026-06-25","cited_by_count":1,"area":"agents"},{"id":"2607.25379","title":"Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response","created":"2026-07-28","cited_by_count":1,"area":"agents"},{"id":"2607.27951","title":"Safeguards Based on Copyable Context Cannot Provide Reliable Safety for LLMs","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2608.05144","title":"Argus: A General-Purpose Agentic Reasoning Runtime for Long-Horizon Tasks","created":"2026-08-05","cited_by_count":1,"area":"agents"},{"id":"2608.06663","title":"The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents","created":"2026-08-07","cited_by_count":1,"area":"lr"},{"id":"2608.14426","title":"The Dynamics of Intelligence Explosions","created":"2026-08-14","cited_by_count":1,"area":null},{"id":"2608.30478","title":"Agents in the Large: Perception-Centered Architecture for Persistent Agents","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2609.04298","title":"Harbor Adapters and Harbor-Index: Infrastructure and a Curated Meta-Dataset for Large-Scale Agentic Evaluation","created":"2026-09-03","cited_by_count":1,"area":"agents"},{"id":"2505.13638","title":"4Hammer: a board-game reinforcement learning environment for the hour long time frame","created":"2025-05-19","cited_by_count":0,"area":"deeprl"}],"next_cursor":"100"}