{"total":30,"rows":[{"id":"2509.02350","title":"Implicit Reasoning in Large Language Models: A Comprehensive Survey","created":"2025-09-02","cited_by_count":43,"area":"lr"},{"id":"2601.05175","title":"VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice","created":"2026-01-08","cited_by_count":21,"area":"lr"},{"id":"2510.08457","title":"ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping","created":"2025-10-09","cited_by_count":17,"area":"lr"},{"id":"2510.04474","title":"DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization","created":"2025-10-06","cited_by_count":16,"area":"lr"},{"id":"2601.21919","title":"Self-Compression of Chain-of-Thought via Multi-Agent Reinforcement Learning","created":"2026-01-29","cited_by_count":13,"area":"lr"},{"id":"2509.25426","title":"RADAR: Reasoning-Ability and Difficulty-Aware Routing for Reasoning LLMs","created":"2025-09-29","cited_by_count":6,"area":"lr"},{"id":"2510.09133","title":"On the Provable Performance Guarantee of Efficient Reasoning Models","created":"2025-10-10","cited_by_count":6,"area":"lr"},{"id":"2510.09883","title":"DELTA: Dynamic Layer-Aware Token Attention for Efficient Long-Context Reasoning","created":"2025-10-10","cited_by_count":6,"area":"lr"},{"id":"2605.05980","title":"TACT: Mitigating Overthinking and Overacting in Coding Agents via Activation Steering","created":"2026-05-07","cited_by_count":6,"area":"lr"},{"id":"2508.20373","title":"NPG-Muse: Scaling Long Chain-of-Thought Reasoning with NP-Hard Graph Problems","created":"2025-08-28","cited_by_count":5,"area":"lr"},{"id":"2510.08026","title":"PEAR: Phase Entropy Aware Reward for Efficient Reasoning","created":"2025-10-09","cited_by_count":5,"area":"lr"},{"id":"2510.02249","title":"Explore Briefly, Then Decide: Mitigating LLM Overthinking via Cumulative Entropy Regulation","created":"2025-10-02","cited_by_count":4,"area":"lr"},{"id":"2510.08163","title":"ARM2: Adaptive Reasoning Model with Vision Understanding and Executable Code","created":"2025-10-09","cited_by_count":4,"area":"lr"},{"id":"2602.01148","title":"Capabilities and Fundamental Limits of Latent Chain-of-Thought","created":"2026-02-01","cited_by_count":4,"area":"lr"},{"id":"2603.12372","title":"Efficient Reasoning with Balanced Thinking","created":"2026-03-12","cited_by_count":4,"area":"lr"},{"id":"2508.09460","title":"Towards Self-cognitive Exploration: Metacognitive Knowledge Graph Retrieval Augmented Generation","created":"2025-08-13","cited_by_count":2,"area":"lr"},{"id":"2510.21007","title":"Can Confidence Estimates Decide When Chain-of-Thought Is Necessary for LLMs?","created":"2025-10-23","cited_by_count":2,"area":"lr"},{"id":"2601.23032","title":"Guided by Trajectories: Repairing and Rewarding Tool-Use Trajectories for Tool-Integrated Reasoning","created":"2026-01-30","cited_by_count":2,"area":"lr"},{"id":"2602.12113","title":"Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty","created":"2026-02-12","cited_by_count":2,"area":"lr"},{"id":"2604.05355","title":"ETR: Entropy Trend Reward for Efficient Chain-of-Thought Reasoning","created":"2026-04-07","cited_by_count":2,"area":"lr"},{"id":"2608.04771","title":"Fewer Tokens, Smaller Cache: Reward-Coordinated Efficient Reasoning","created":"2026-08-05","cited_by_count":2,"area":"lr"},{"id":"2511.10201","title":"EffiReason-Bench: A Unified Benchmark for Evaluating and Advancing Efficient Reasoning in Large Language Models","created":"2025-11-13","cited_by_count":1,"area":"lr"},{"id":"2603.20212","title":"Fast-Slow Thinking RM: Efficient Integration of Scalar and Generative Reward Models","created":"2026-03-02","cited_by_count":1,"area":"lr"},{"id":"2510.24811","title":"ProofSketch: Efficient Verified Reasoning for Large Language Models","created":"2025-10-28","cited_by_count":0,"area":"lr"},{"id":"2601.22790","title":"Conditional Performance Guarantee for Large Reasoning Models","created":"2026-01-30","cited_by_count":0,"area":"lr"},{"id":"2604.08232","title":"HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation","created":"2026-04-09","cited_by_count":0,"area":"lr"},{"id":"2605.10195","title":"Breaking the Reward Barrier: Accelerating Tree-of-Thought Reasoning via Speculative Exploration","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2608.10928","title":"ThinkRetrieve: Retrieval-Augmented Reasoning Traces for Test-Time Scaling","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2609.17019","title":"SKIP: a Self-knowledge-guided Step-wise Preference Learning Framework for Concise Reasoning","created":"2026-09-15","cited_by_count":0,"area":"lr"},{"id":"2609.27156","title":"Giving Credit Where It's Due: Redundancy-Aware Learning for Efficient Reasoning","created":"2026-09-22","cited_by_count":0,"area":"lr"}],"next_cursor":null}