{"total":18,"rows":[{"id":"2507.00432","title":"Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning","created":"2025-07-01","cited_by_count":106,"area":"lr"},{"id":"2505.08243","title":"Training Strategies for Efficient Embodied Reasoning","created":"2025-05-13","cited_by_count":55,"area":"lr"},{"id":"2212.10923","title":"Language Models as Inductive Reasoners","created":"2022-12-21","cited_by_count":32,"area":"lr"},{"id":"2503.04543","title":"Keeping Yourself is Important in Downstream Tuning Multimodal Large Language Model","created":"2025-03-06","cited_by_count":16,"area":"lr"},{"id":"2502.04040","title":"Safety Reasoning with Guidelines","created":"2025-02-06","cited_by_count":15,"area":"lr"},{"id":"2312.15230","title":"PERP: Rethinking the Prune-Retrain Paradigm in the Era of LLMs","created":"2023-12-23","cited_by_count":14,"area":"lr"},{"id":"2306.07536","title":"TART: A plug-and-play Transformer module for task-agnostic reasoning","created":"2023-06-13","cited_by_count":10,"area":"lr"},{"id":"2602.09305","title":"Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation","created":"2026-02-10","cited_by_count":7,"area":"lr"},{"id":"2602.12405","title":"Self-Refining Vision Language Model for Robotic Failure Detection and Reasoning","created":"2026-02-12","cited_by_count":7,"area":"lr"},{"id":"2404.16068","title":"SemEval-2024 Task 9: BRAINTEASER: A Novel Task Defying Common Sense","created":"2024-04-22","cited_by_count":6,"area":"lr"},{"id":"2409.09721","title":"Finetuning CLIP to Reason about Pairwise Differences","created":"2024-09-15","cited_by_count":6,"area":"lr"},{"id":"2306.14035","title":"Thinking Like an Annotator: Generation of Dataset Labeling Instructions","created":"2023-06-24","cited_by_count":4,"area":"lr"},{"id":"2602.06359","title":"Training Data Selection with Gradient Orthogonality for Efficient Domain Adaptation","created":"2026-02-06","cited_by_count":3,"area":"lr"},{"id":"2601.04670","title":"Learning Dynamics in RL Post-Training for Language Models","created":"2026-01-08","cited_by_count":2,"area":"lr"},{"id":"2601.09233","title":"GIFT: Reconciling Post-Training Objectives via Variational Finite-Temperature Gibbs Initialization","created":"2026-01-14","cited_by_count":2,"area":"lr"},{"id":"2606.09396","title":"PriFT: Prior-Support Guided Supervised Fine-Tuning","created":"2026-06-08","cited_by_count":2,"area":"lr"},{"id":"2511.07070","title":"RedOne 2.0: Rethinking Domain-specific LLM Post-Training in Social Networking Services","created":"2025-11-10","cited_by_count":1,"area":"lr"},{"id":"2610.08814","title":"Route-Verify-Vote: Procedure-Conditioned Self-Consistency for Mixed-Domain Reasoning","created":"2026-09-23","cited_by_count":0,"area":"lr"}],"next_cursor":null}