{"total":17,"rows":[{"id":"2405.07863","title":"RLHF Workflow: From Reward Modeling to Online RLHF","created":"2024-05-13","cited_by_count":267,"area":"lr"},{"id":"2504.20595","title":"ReasonIR: Training Retrievers for Reasoning Tasks","created":"2025-04-29","cited_by_count":77,"area":"lr"},{"id":"2410.04585","title":"Reasoning-Enhanced Healthcare Predictions with Knowledge Graph Community Retrieval","created":"2024-10-06","cited_by_count":45,"area":"lr"},{"id":"2408.01107","title":"BioRAG: A RAG-LLM Framework for Biological Question Reasoning","created":"2024-08-02","cited_by_count":43,"area":"lr"},{"id":"2502.15854","title":"Enhancing Domain-Specific Retrieval-Augmented Generation: Synthetic Data Generation and Evaluation using Reasoning Models","created":"2025-02-21","cited_by_count":4,"area":"lr"},{"id":"2505.09068","title":"S-DAT: A Multilingual, GenAI-Driven Framework for Automated Divergent Thinking Assessment","created":"2025-05-14","cited_by_count":3,"area":"lr"},{"id":"2602.23864","title":"RUMAD: Reinforcement-Unifying Multi-Agent Debate","created":"2026-02-27","cited_by_count":3,"area":"lr"},{"id":"2510.10454","title":"Traj-CoA: Patient Trajectory Modeling via Chain-of-Agents for Lung Cancer Risk Prediction","created":"2025-10-12","cited_by_count":2,"area":"lr"},{"id":"2601.05549","title":"Efficient Temporal-aware Matryoshka Adaptation for Temporal Information Retrieval","created":"2026-01-09","cited_by_count":2,"area":"lr"},{"id":"2609.36059","title":"Mnemon: Raw Records, Fast Judgments, Slow Thoughts","created":"2026-09-28","cited_by_count":2,"area":"lr"},{"id":"2507.15874","title":"Why Braking? Scenario Extraction and Reasoning Utilizing LLM","created":"2025-07-17","cited_by_count":1,"area":"lr"},{"id":"2601.07790","title":"Benchmarking Small Language Models and Small Reasoning Language Models on System Log Severity Classification","created":"2026-01-12","cited_by_count":1,"area":"lr"},{"id":"2606.04231","title":"MM-BizRAG: Rethinking Multimodal Retrieval-Augmented Generation for General Purpose Enterprise Q&A","created":"2026-06-02","cited_by_count":1,"area":"lr"},{"id":"2510.17910","title":"Interpretability Framework for LLMs in Undergraduate Calculus","created":"2025-10-19","cited_by_count":0,"area":"lr"},{"id":"2604.07079","title":"MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaL","created":"2026-04-08","cited_by_count":0,"area":"lr"},{"id":"2604.12133","title":"Towards Platonic Representation for Table Reasoning: A Foundation for Permutation-Invariant Retrieval","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2606.21123","title":"A Multi-Agent Audit Framework for High-Stakes Reasoning: Evaluation and Interpretability in Clinical Mental Health Screening","created":"2026-06-19","cited_by_count":0,"area":"lr"}],"next_cursor":null}