{"total":23,"rows":[{"id":"2503.23157","title":"Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL","created":"2025-03-29","cited_by_count":59,"area":"lr"},{"id":"2508.02298","title":"CAPO: Towards Enhancing LLM Reasoning through Generative Credit Assignment","created":"2025-08-04","cited_by_count":26,"area":"lr"},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2601.21037","title":"Thinking in Frames: How Visual Context and Test-Time Scaling Empower Video Reasoning","created":"2026-01-28","cited_by_count":10,"area":"lr"},{"id":"2508.04524","title":"RAIDX: A Retrieval-Augmented Generation and GRPO Reinforcement Learning Framework for Explainable Deepfake Detection","created":"2025-08-06","cited_by_count":8,"area":"lr"},{"id":"2506.18512","title":"MedTVT-R1: A Multimodal LLM Empowering Medical Reasoning and Diagnosis","created":"2025-06-23","cited_by_count":7,"area":"lr"},{"id":"2505.20296","title":"Reasoning LLMs are Wandering Solution Explorers","created":"2025-05-26","cited_by_count":6,"area":"lr"},{"id":"2510.01719","title":"What MLLMs Learn about When they Learn about Multimodal Reasoning","created":"2025-10-02","cited_by_count":6,"area":"lr"},{"id":"2604.00558","title":"STAR: Mitigating Cascading Errors in Spatial Reasoning via Turn-point Alignment and Segment-level DPO","created":"2026-04-01","cited_by_count":4,"area":"lr"},{"id":"2511.19923","title":"Distilling Counterfactual Reasoning from Language to Vision: Causal Graph Guided Post-Training for Video Understanding","created":"2025-11-25","cited_by_count":2,"area":"lr"},{"id":"2604.17912","title":"Learning to Correct: Calibrated Reinforcement Learning for Multi-Attempt Chain-of-Thought","created":"2026-04-20","cited_by_count":2,"area":"lr"},{"id":"2604.22868","title":"Probing Visual Planning in Image Editing Models","created":"2026-04-23","cited_by_count":2,"area":"lr"},{"id":"2605.28008","title":"Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training","created":"2026-05-27","cited_by_count":2,"area":"lr"},{"id":"2511.00710","title":"Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models","created":"2025-11-01","cited_by_count":1,"area":"lr"},{"id":"2511.18084","title":"The Alignment Paradox of Medical Large Language Models in Infertility Care: Decoupling Algorithmic Improvement from Clinical Decision-making Quality","created":"2025-11-22","cited_by_count":1,"area":"lr"},{"id":"2512.24532","title":"From Building Blocks to Planning: Multi-Step Spatial Reasoning in LLMs with Reinforcement Learning","created":"2025-12-31","cited_by_count":1,"area":"lr"},{"id":"2604.01610","title":"GraphWalk: Enabling Reasoning in Large Language Models through Tool-Based Graph Navigation","created":"2026-04-02","cited_by_count":1,"area":"lr"},{"id":"2604.09338","title":"Mind the Gap Between Spatial Reasoning and Acting! Step-by-Step Evaluation of Agents With Spatial-Gym","created":"2026-04-10","cited_by_count":1,"area":"lr"},{"id":"2503.18769","title":"AlphaSpace: Enabling Robotic Actions through Semantic Tokenization and Symbolic Reasoning","created":"2025-03-24","cited_by_count":0,"area":"lr"},{"id":"2509.22688","title":"Robust Object Detection for Autonomous Driving via Curriculum-Guided Group Relative Policy Optimization","created":"2025-09-19","cited_by_count":0,"area":"lr"},{"id":"2605.28144","title":"Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial Reasoning","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2609.11900","title":"MindTopo: Can Foundation Models Reason in Topological Space?","created":"2026-09-10","cited_by_count":0,"area":"lr"},{"id":"2609.16076","title":"The Imitation Game: When LLMs Learn to Reason Like Programs via Code-Centric Reasoning Data Synthesis","created":"2026-09-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}