{"total":22,"rows":[{"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":"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":"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":"2605.10310","title":"Positive Alignment: Artificial Intelligence for Human Flourishing","created":"2026-05-11","cited_by_count":5,"area":null},{"id":"2602.06357","title":"LLM-SAA: LLM-persona Generated Distributions for Decision-making","created":"2026-02-06","cited_by_count":3,"area":null},{"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":"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":"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":"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":"2511.15830","title":"Mini Amusement Parks (MAPs): A Testbed for Modelling Business Decisions","created":"2025-11-19","cited_by_count":1,"area":null},{"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":"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":"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":"2608.10475","title":"Evaluating Rational Contracting in Natural Language","created":"2026-08-11","cited_by_count":0,"area":null},{"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":"2609.19113","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":"2609.33023","title":"SRE-Marathon: A Continuous, Change-Driven Benchmark for Autonomous Site Reliability Agents","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.02122","title":"Argo-Bench: Evaluating Data Agents on Enterprise-Scale Workflows","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.16070","title":"Understanding and Reducing Misalignment in Persuasion Optimization","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}