{"total":23,"rows":[{"id":"2606.15007","title":"Nemotron 3 Ultra: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-06-12","cited_by_count":42,"area":"lr"},{"id":"2604.13010","title":"Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation","created":"2026-04-14","cited_by_count":33,"area":"lr"},{"id":"2605.05835","title":"Evaluation Awareness in Language Models Has Limited Effect on Behaviour","created":"2026-05-07","cited_by_count":7,"area":"lr"},{"id":"2604.12378","title":"ReasonXL: Shifting LLM Reasoning Language Without Sacrificing Performance","created":"2026-04-14","cited_by_count":5,"area":"lr"},{"id":"2605.07579","title":"Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal States","created":"2026-05-08","cited_by_count":5,"area":"lr"},{"id":"2606.15378","title":"Rethinking the Role of Efficient Attention in Hybrid Architectures","created":"2026-06-13","cited_by_count":5,"area":"lr"},{"id":"2607.28449","title":"Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models","created":"2026-07-30","cited_by_count":5,"area":"lr"},{"id":"2605.15726","title":"Nudging Beyond the Comfort Zone: Efficient Strategy-Guided Exploration for RLVR","created":"2026-05-15","cited_by_count":4,"area":"lr"},{"id":"2602.06291","title":"Judging What We Cannot Solve: A Consequence-Based Approach for Oracle-Free Evaluation of Research-Level Math","created":"2026-02-06","cited_by_count":1,"area":"lr"},{"id":"2602.11937","title":"Extending Puzzle for Mixture-of-Experts Reasoning Models with Application to GPT-OSS Acceleration","created":"2026-02-12","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":"2602.14265","title":"STATe-of-Thoughts: Structured Action Templates for Tree-of-Thoughts","created":"2026-02-15","cited_by_count":0,"area":"lr"},{"id":"2605.20364","title":"When Reasoning Supervision Hurts: TTCW-Based Long-Form Literary Review Generation","created":"2026-05-19","cited_by_count":0,"area":"lr"},{"id":"2606.14240","title":"AFFORDANCE20Q: Evaluating Affordance Reasoning from Physical Properties","created":"2026-06-12","cited_by_count":0,"area":"lr"},{"id":"2606.29067","title":"ThinkProbe: Beyond Accuracy -- Structural Profiling of Open-Ended LLM Reasoning Traces via Non-Generative Thought Graphs","created":"2026-06-27","cited_by_count":0,"area":"lr"},{"id":"2607.26845","title":"Thinking Under Uncertainty: Evidence Use and Information-Seeking in Language Models","created":"2026-07-29","cited_by_count":0,"area":"lr"},{"id":"2608.12391","title":"Unified Multi-Dimensional Benchmark for Complex Graph Reasoning in Large Language Models","created":"2026-08-02","cited_by_count":0,"area":"lr"},{"id":"2608.12585","title":"Reasoning Jury: Multi-Model Consensus for Evaluating Reasoning Traces","created":"2026-08-12","cited_by_count":0,"area":"lr"},{"id":"2609.15987","title":"Bellman Policy Optimization","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.31571","title":"Strategically Diverse Sampling for Self-Training","created":"2026-09-25","cited_by_count":0,"area":"lr"},{"id":"2609.32932","title":"Counting on Thinking: Tracing Evidence Integration in Language Models","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.38958","title":"Targeted Retrieval, Compact Representations: How CoT Reasoning Improves Long-Context Counting","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.19362","title":"Tail Competition Explains Scaling in Best-of-N Sampling for Verifiable Problems","created":"2026-10-14","cited_by_count":0,"area":"lr"}],"next_cursor":null}