{"total":20,"rows":[{"id":"2507.11948","title":"Kevin: Multi-Turn RL for Generating CUDA Kernels","created":"2025-07-16","cited_by_count":78,"area":null},{"id":"2506.10341","title":"Formalizing Learning from Language Feedback with Provable Guarantees","created":"2025-06-12","cited_by_count":13,"area":null},{"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":"2604.06543","title":"The Illusion of Stochasticity in LLMs","created":"2026-04-08","cited_by_count":9,"area":null},{"id":"2604.19809","title":"MIRROR: A Hierarchical Benchmark for Metacognitive Calibration in Large Language Models","created":"2026-04-15","cited_by_count":6,"area":null},{"id":"2508.01724","title":"ReflecSched: Solving Dynamic Flexible Job-Shop Scheduling via LLM-Powered Hierarchical Reflection","created":"2025-08-03","cited_by_count":5,"area":null},{"id":"2509.24923","title":"When Greedy Wins: Emergent Exploitation Bias in Meta-Bandit LLM Training","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2510.03413","title":"Report of the 2025 Workshop on Next-Generation Ecosystems for Scientific Computing: Harnessing Community, Software, and AI for Cross-Disciplinary Team Science","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2511.06148","title":"Large Language Models Develop Novel Social Biases Through Adaptive Exploration","created":"2025-11-08","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":"2509.24435","title":"Alternatives To Next Token Prediction In Text Generation -- A Survey","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2601.12945","title":"A Component-Based Survey of Interactions between Large Language Models and Multi-Armed Bandits","created":"2026-01-19","cited_by_count":1,"area":null},{"id":"2604.05859","title":"When Do We Need LLMs? A Diagnostic for Language-Driven Bandits","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.17244","title":"DORA Explorer: Improving the Exploration Ability of LLMs Without Training","created":"2026-04-19","cited_by_count":0,"area":null},{"id":"2609.31401","title":"Decodable In-Context State and Model Output Across Training","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.33061","title":"LLM sequential decision making under uncertainty in biochemical domains","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.06191","title":"Judged Useless, Queried Anyway: Tool-Using Agents Rarely Turn Their Own Evidence Judgments into Stopping Decisions","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.08670","title":"Principled Under Pressure: Post-Training Decides Whether LLMs Act on Their Own Moral Judgment","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.18579","title":"Reading Right, Acting Wrong: Diagnosing Decision Failures of System One Models in Agent Loops","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}