{"total":15,"rows":[{"id":"2508.16949","title":"Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning","created":"2025-08-23","cited_by_count":63,"area":"lr"},{"id":"2508.06924","title":"AR-GRPO: Training Autoregressive Image Generation Models via Reinforcement Learning","created":"2025-08-09","cited_by_count":22,"area":"lr"},{"id":"2511.02309","title":"The Sequential Edge: Inverse-Entropy Voting Beats Parallel Self-Consistency at Matched Compute","created":"2025-11-04","cited_by_count":11,"area":"lr"},{"id":"2602.18232","title":"Thinking by Subtraction: Confidence-Driven Contrastive Decoding for LLM Reasoning","created":"2026-02-20","cited_by_count":6,"area":"lr"},{"id":"2510.13940","title":"Less is More: Improving LLM Reasoning with Minimal Test-Time Intervention","created":"2025-10-15","cited_by_count":5,"area":"lr"},{"id":"2506.06971","title":"Chain-of-Code Collapse: Reasoning Failures in LLMs via Adversarial Prompting in Code Generation","created":"2025-06-08","cited_by_count":4,"area":"lr"},{"id":"2602.07882","title":"Rethinking Code Complexity Through the Lens of Large Language Models","created":"2026-02-08","cited_by_count":4,"area":"lr"},{"id":"2509.25835","title":"Chain-in-Tree: Back to Sequential Reasoning in LLM Tree Search","created":"2025-09-30","cited_by_count":3,"area":"lr"},{"id":"2604.14528","title":"Dissecting Failure Dynamics in Large Language Model Reasoning","created":"2026-04-16","cited_by_count":2,"area":"lr"},{"id":"2602.15332","title":"Directional Reasoning Trajectory Change (DRTC): Identifying Critical Trace Segments in Reasoning Models","created":"2026-02-17","cited_by_count":1,"area":"lr"},{"id":"2605.19358","title":"Taming the Thinker: Conditional Entropy Shaping for Adaptive LLM Reasoning","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2605.26172","title":"ARBITER: Reasoning Trajectory Basins and Majority Vote Failures in Test-Time Sampling","created":"2026-05-25","cited_by_count":1,"area":"lr"},{"id":"2605.31561","title":"What Am I Missing? Question-Answering as Hidden State Probing","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2602.02427","title":"Embedding Perturbation may Better Reflect Intermediate-Step Uncertainty in LLM Reasoning","created":"2026-02-02","cited_by_count":0,"area":"lr"},{"id":"2606.16620","title":"Entropy-Gated Latent Recursion","created":"2026-06-15","cited_by_count":0,"area":"lr"}],"next_cursor":null}