{"total":16,"rows":[{"id":"2407.21787","title":"Large Language Monkeys: Scaling Inference Compute with Repeated Sampling","created":"2024-07-31","cited_by_count":991,"area":null},{"id":"2311.18232","title":"LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models","created":"2023-11-30","cited_by_count":88,"area":null},{"id":"2401.02994","title":"Blending Is All You Need: Cheaper, Better Alternative to Trillion-Parameters LLM","created":"2024-01-04","cited_by_count":27,"area":null},{"id":"2410.12916","title":"MSc-SQL: Multi-Sample Critiquing Small Language Models For Text-To-SQL Translation","created":"2024-10-16","cited_by_count":19,"area":null},{"id":"2307.14117","title":"Leveraging Implicit Feedback from Deployment Data in Dialogue","created":"2023-07-26","cited_by_count":14,"area":null},{"id":"2409.06820","title":"PingPong: A Benchmark for Role-Playing Language Models with User Emulation and Multi-Model Evaluation","created":"2024-09-10","cited_by_count":10,"area":null},{"id":"2606.30850","title":"BayesBench: Evaluating LLM Belief Trajectories Under Multi-Turn Evidence Accumulation","created":"2026-06-29","cited_by_count":7,"area":null},{"id":"2601.03764","title":"Learning Shrinks the Hard Tail: Training-Dependent Inference Scaling in a Solvable Linear Model","created":"2026-01-07","cited_by_count":6,"area":null},{"id":"2406.15000","title":"Unveiling the Impact of Multi-Modal Interactions on User Engagement: A Comprehensive Evaluation in AI-driven Conversations","created":"2024-06-21","cited_by_count":4,"area":null},{"id":"2509.23166","title":"Test-Time Policy Adaptation for Enhanced Multi-Turn Interactions with LLMs","created":"2025-09-27","cited_by_count":3,"area":null},{"id":"2304.09865","title":"Safer Conversational AI as a Source of User Delight","created":"2023-04-18","cited_by_count":2,"area":null},{"id":"2306.02979","title":"The Chai Platform's AI Safety Framework","created":"2023-06-05","cited_by_count":1,"area":null},{"id":"2507.17234","title":"CLARIFID: Improving Radiology Report Generation by Reinforcing Clinically Accurate Impressions and Enforcing Detailed Findings","created":"2025-07-23","cited_by_count":1,"area":null},{"id":"2410.11009","title":"Enhancing AI Assisted Writing with One-Shot Implicit Negative Feedback","created":"2024-10-14","cited_by_count":0,"area":null},{"id":"2509.13391","title":"The Intercepted Self: How Generative AI Challenges the Dynamics of the Relational Self","created":"2025-09-16","cited_by_count":0,"area":null},{"id":"2607.27816","title":"Beyond Borrowed Histories: Person-Aligned User Simulation for Interactive Role-Playing Evaluation","created":"2026-07-30","cited_by_count":0,"area":null}],"next_cursor":null}