{"total":80,"rows":[{"id":"2602.15763","title":"GLM-5: from Vibe Coding to Agentic Engineering","created":"2026-02-17","cited_by_count":587,"area":"agents"},{"id":"2504.19678","title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","created":"2025-04-28","cited_by_count":149,"area":"lr"},{"id":"2507.07998","title":"PyVision: Agentic Vision with Dynamic Tooling","created":"2025-07-10","cited_by_count":79,"area":"agents"},{"id":"2509.09677","title":"The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs","created":"2025-09-11","cited_by_count":64,"area":null},{"id":"2511.01824","title":"Simulating Environments with Reasoning Models for Agent Training","created":"2025-11-03","cited_by_count":57,"area":"lr"},{"id":"2602.11964","title":"Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments","created":"2026-02-12","cited_by_count":33,"area":"agents"},{"id":"2604.05172","title":"ClawsBench: Evaluating Capability and Safety of LLM Productivity Agents in Simulated Workspaces","created":"2026-04-06","cited_by_count":33,"area":"agents"},{"id":"2509.17158","title":"ARE: Scaling Up Agent Environments and Evaluations","created":"2025-09-21","cited_by_count":30,"area":"agents"},{"id":"2604.24964","title":"Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks","created":"2026-04-27","cited_by_count":21,"area":"agents"},{"id":"2602.05073","title":"Uncertainty Quantification in LLM Agents: Foundations, Emerging Challenges, and Opportunities","created":"2026-02-04","cited_by_count":20,"area":"agents"},{"id":"2606.05806","title":"When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents","created":"2026-06-04","cited_by_count":17,"area":"lr"},{"id":"2604.15267","title":"CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas","created":"2026-04-16","cited_by_count":16,"area":"lr"},{"id":"2603.07980","title":"\\$OneMillion-Bench: How Far are Language Agents from Human Experts?","created":"2026-03-09","cited_by_count":13,"area":"agents"},{"id":"2601.22130","title":"World of Workflows: A Benchmark for Bringing World Models to Enterprise Systems","created":"2026-01-29","cited_by_count":11,"area":"wm"},{"id":"2604.01212","title":"$\\texttt{YC-Bench}$: Benchmarking AI Agents for Long-Term Planning and Consistent Execution","created":"2026-04-01","cited_by_count":11,"area":"agents"},{"id":"2503.18825","title":"EconEvals: Benchmarks and Litmus Tests for Economic Decision-Making by LLM Agents","created":"2025-03-24","cited_by_count":10,"area":"agents"},{"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":"2603.03258","title":"Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals","created":"2026-03-03","cited_by_count":9,"area":"agents"},{"id":"2604.27043","title":"CL-bench Life: Can Language Models Learn from Real-Life Context?","created":"2026-04-29","cited_by_count":9,"area":null},{"id":"2602.12631","title":"AI Agents for Inventory Control: Human-LLM-OR Complementarity","created":"2026-02-13","cited_by_count":8,"area":"agents"},{"id":"2606.16613","title":"CoffeeBench: Benchmarking Long-Horizon LLM Agents in Heterogeneous Multi-Agent Economies","created":"2026-06-15","cited_by_count":8,"area":"agents"},{"id":"2509.07961","title":"Probing the Preferences of a Language Model: Integrating Verbal and Behavioral Tests of AI Welfare","created":"2025-09-09","cited_by_count":7,"area":"alignment"},{"id":"2605.15188","title":"FutureSim: Replaying World Events to Evaluate Adaptive Agents","created":"2026-05-14","cited_by_count":7,"area":null},{"id":"2510.00857","title":"ManagerBench: Evaluating the Safety-Pragmatism Trade-off in Autonomous LLMs","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2604.14140","title":"LongCoT: Benchmarking Long-Horizon Chain-of-Thought Reasoning","created":"2026-04-15","cited_by_count":6,"area":"lr"},{"id":"2606.15862","title":"RetailBench: Benchmarking long horizon reasoning and coherent decision making of LLM agents in realistic retail environments","created":"2026-06-14","cited_by_count":6,"area":"lr"},{"id":"2606.18543","title":"CEO-Bench: Can Agents Play the Long Game?","created":"2026-06-16","cited_by_count":6,"area":"agents"},{"id":"2607.28956","title":"MerchantBench: Benchmarking LLM Agents for Long-Term Coherence in E-Commerce Operations","created":"2026-07-31","cited_by_count":6,"area":"agents"},{"id":"2604.09678","title":"NetAgentBench: A State-Centric Benchmark for Evaluating Agentic Network Configuration","created":"2026-04-03","cited_by_count":5,"area":"agents"},{"id":"2605.10310","title":"Positive Alignment: Artificial Intelligence for Human Flourishing","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2512.15892","title":"VET Your Agent: Towards Host-Independent Autonomy via Verifiable Execution Traces","created":"2025-12-17","cited_by_count":4,"area":"agents"},{"id":"2602.06357","title":"LLM-SAA: LLM-persona Generated Distributions for Decision-making","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2602.10153","title":"Basic Legibility Protocols Improve Trusted Monitoring","created":"2026-02-09","cited_by_count":3,"area":"safety"},{"id":"2605.17829","title":"Interactive Evaluation Requires a Design Science","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2606.00341","title":"ROGUE: Evaluating Corrigibility Failures in Frontier Computer-Use Agents","created":"2026-05-29","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":"2510.21860","title":"Butter-Bench: Evaluating LLM Controlled Robots for Practical Intelligence","created":"2025-10-23","cited_by_count":2,"area":null},{"id":"2602.07839","title":"TodoEvolve: Learning to Architect Agent Planning Systems","created":"2026-02-08","cited_by_count":2,"area":null},{"id":"2602.09514","title":"EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies","created":"2026-02-10","cited_by_count":2,"area":"agents"},{"id":"2604.07733","title":"CivBench: Progress-Based Evaluation for LLMs' Strategic Decision-Making in Civilization V","created":"2026-04-09","cited_by_count":2,"area":"agents"},{"id":"2605.17698","title":"Agent Bazaar: Enabling Economic Alignment in Multi-Agent Marketplaces","created":"2026-05-17","cited_by_count":2,"area":"agents"},{"id":"2605.21401","title":"Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment","created":"2026-05-20","cited_by_count":2,"area":null},{"id":"2607.25398","title":"HANDBOOK.md: A Benchmark for Long-Context Agentic Instruction Following","created":"2026-07-28","cited_by_count":2,"area":"agents"},{"id":"2608.08621","title":"Business Arena: Benchmarking LLM Agents in a Realistic Marketplace","created":"2026-08-09","cited_by_count":2,"area":"agents"},{"id":"2608.14825","title":"Emergent Misaligned Communication in Long-Horizon Multi-Agent LLM Commerce","created":"2026-08-14","cited_by_count":2,"area":"agents"},{"id":"2608.30730","title":"E-Commerce Bench: Evaluating LLM Agents on Long-Horizon Autonomous Business Operation","created":"2026-08-31","cited_by_count":2,"area":"agents"},{"id":"2609.19801","title":"DeliveryGym: An RL Environment for Long-Horizon Embodied Agent Planning with Adaptive Curriculum","created":"2026-09-17","cited_by_count":2,"area":"agents"},{"id":"2509.02655","title":"BioBlue: Systematic runaway-optimiser-like LLM failure modes on biologically and economically aligned AI safety benchmarks for LLMs with simplified observation format","created":"2025-09-02","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":"2511.15830","title":"Mini Amusement Parks (MAPs): A Testbed for Modelling Business Decisions","created":"2025-11-19","cited_by_count":1,"area":null},{"id":"2603.03148","title":"From Language to Action: Can LLM-Based Agents Be Used for Embodied Robot Cognition?","created":"2026-03-03","cited_by_count":1,"area":"agents"},{"id":"2603.16453","title":"RetailBench: Evaluating Long-Horizon Autonomous Decision-Making and Strategy Stability of LLM Agents in Realistic Retail Environments","created":"2026-03-17","cited_by_count":1,"area":"agents"},{"id":"2604.00392","title":"Beyond Task Completion: A Verification-vs.-Conformance Gap in Tool-Evolving Agents","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2604.01444","title":"Cooking Up Risks: Benchmarking and Reducing Food Safety Risks in Large Language Models","created":"2026-04-01","cited_by_count":1,"area":"safety"},{"id":"2606.19613","title":"StaminaBench: Stress-Testing Coding Agents over 100 Interaction Turns","created":"2026-06-17","cited_by_count":1,"area":"agents"},{"id":"2607.13618","title":"STOCKTAKE: Measuring the Gap Between Perception and Action in LLM Agents with a Fair Oracle","created":"2026-07-15","cited_by_count":1,"area":"agents"},{"id":"2607.14989","title":"OmniaBench: Benchmarking General AI Agents Across Diverse Scenarios","created":"2026-07-16","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":"2608.18423","title":"FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents","created":"2026-08-19","cited_by_count":1,"area":"agents"},{"id":"2609.02580","title":"Competitive Market Behavior of LLMs","created":"2026-09-02","cited_by_count":1,"area":"agents"},{"id":"2509.26331","title":"AI Playing Business Games: Benchmarking Large Language Models on Managerial Decision-Making in Dynamic Simulations","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2601.05570","title":"Crisis-Bench: Benchmarking Strategic Ambiguity and Reputation Management in Large Language Models","created":"2026-01-09","cited_by_count":0,"area":"alignment"},{"id":"2602.13209","title":"LemonadeBench: Evaluating the Economic Intuition of Large Language Models in Simple Markets","created":"2026-01-14","cited_by_count":0,"area":null},{"id":"2606.19308","title":"Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2606.22909","title":"Graph-Enhanced Large Language Models for Spatial Search","created":"2026-06-22","cited_by_count":0,"area":"lr"},{"id":"2608.10475","title":"Evaluating Rational Contracting in Natural Language","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.02459","title":"CivBench: A Long-Horizon Benchmark for Tool-Mediated Agents in Civilization VI","created":"2026-09-02","cited_by_count":0,"area":"agents"},{"id":"2609.05435","title":"AhaBench: Do Agents Turn Experience into Reusable Insights? A Long-Horizon Benchmark for Continual Learning","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2609.17320","title":"Emergence World: Adversarial Stress-Testing of Long-Horizon Multi-Agent Systems","created":"2026-09-15","cited_by_count":0,"area":"agents"},{"id":"2609.19113","title":"Playing log(N)-Questions over Wikipedia Abstracts: How Per-Round Errors Compound Under Information Asymmetry","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.27321","title":"Verifiable Hidden Dynamics Play: Generating Agentic RL Environments from Solved Mechanisms","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.33023","title":"SRE-Marathon: A Continuous, Change-Driven Benchmark for Autonomous Site Reliability Agents","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.34710","title":"FromPitch2Board: Benchmarking LLM Agents in Long-Horizon Football Management","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.39140","title":"Schema: Discovering Unknown Environments via Agentic Program Induction","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.02122","title":"Argo-Bench: Evaluating Data Agents on Enterprise-Scale Workflows","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.06748","title":"BazaarBench: Delegation Safety in Decentralized C2C Marketplaces Run by LLM Agents","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.10942","title":"StoreBench: A Live-Commerce Environment for Evaluating and Training Autonomous Operator Agents","created":"2026-10-07","cited_by_count":0,"area":"agents"},{"id":"2610.16070","title":"Understanding and Reducing Misalignment in Persuasion Optimization","created":"2026-10-12","cited_by_count":0,"area":null},{"id":"2610.19291","title":"Can LLM Agents Efficiently Identify Appliance Faults? Insights From Diagnosing a Simulated Appliance","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.19589","title":"JockeyBench: Evaluating LLM Agents on Horse-Racing Decision-Making","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}