{"total":16,"rows":[{"id":"2508.02120","title":"Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models","created":"2025-08-04","cited_by_count":37,"area":"lr"},{"id":"2510.17238","title":"StreamingThinker: Large Language Models Can Think While Reading","created":"2025-10-20","cited_by_count":15,"area":"lr"},{"id":"2511.15705","title":"GeoVista: Web-Augmented Agentic Visual Reasoning for Geolocalization","created":"2025-11-19","cited_by_count":11,"area":"lr"},{"id":"2510.11184","title":"Reinforcement Learning for Tool-Integrated Interleaved Thinking towards Cross-Domain Generalization","created":"2025-10-13","cited_by_count":7,"area":"lr"},{"id":"2603.02091","title":"Learning from Synthetic Data Improves Multi-hop Reasoning","created":"2026-03-02","cited_by_count":6,"area":"lr"},{"id":"2509.24238","title":"Learning to Ponder: Adaptive Reasoning in Latent Space","created":"2025-09-29","cited_by_count":5,"area":"lr"},{"id":"2512.03176","title":"Plantain: Plan-Answer Interleaved Reasoning","created":"2025-12-02","cited_by_count":5,"area":"lr"},{"id":"2605.03314","title":"When to Think, When to Speak: Learning Disclosure Policies for LLM Reasoning","created":"2026-05-05","cited_by_count":5,"area":"lr"},{"id":"2601.14560","title":"Rewarding How Models Think Pedagogically: Integrating Pedagogical Reasoning and Thinking Rewards for LLMs in Education","created":"2026-01-21","cited_by_count":3,"area":"lr"},{"id":"2603.05867","title":"TumorChain: Interleaved Multimodal Chain-of-Thought Reasoning for Traceable Clinical Tumor Analysis","created":"2026-03-06","cited_by_count":3,"area":"lr"},{"id":"2608.22429","title":"Think with Structured Grounding: Perceptual Reinforcement Learning for Chart and Visual-Tabular Understanding","created":"2026-08-23","cited_by_count":2,"area":"lr"},{"id":"2510.21853","title":"Policy Optimization Prefers The Path of Least Resistance","created":"2025-10-22","cited_by_count":1,"area":"lr"},{"id":"2601.05300","title":"TIME: Temporally Intelligent Meta-reasoning Engine for Context-Triggered Explicit Reasoning","created":"2026-01-08","cited_by_count":1,"area":"lr"},{"id":"2602.03190","title":"PrAg-PO: Prompt Augmented Policy Optimization for Robust and Diverse Mathematical Reasoning","created":"2026-02-03","cited_by_count":1,"area":"lr"},{"id":"2603.04676","title":"Decoding the Pulse of Reasoning VLMs in Multi-Image Understanding Tasks","created":"2026-03-04","cited_by_count":0,"area":"lr"},{"id":"2605.29568","title":"DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning","created":"2026-05-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}