{"total":65,"rows":[{"id":"2606.02800","title":"Cosmos 3: Omnimodal World Models for Physical AI","created":"2026-06-01","cited_by_count":165,"area":"wm"},{"id":"2604.06132","title":"Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents","created":"2026-04-07","cited_by_count":64,"area":"agents"},{"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":"2604.12374","title":"Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning","created":"2026-04-14","cited_by_count":38,"area":"agents"},{"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":"2603.07685","title":"Scalable Training of Mixture-of-Experts Models with Megatron Core","created":"2026-03-08","cited_by_count":19,"area":"moe"},{"id":"2608.03893","title":"Cross-Model KV Cache Transfer in LLM Families: A Closed-Form Linear Mapping for Prefill Reuse","created":"2026-08-04","cited_by_count":15,"area":"inference"},{"id":"2604.09557","title":"SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding","created":"2026-02-10","cited_by_count":10,"area":"inference"},{"id":"2603.14360","title":"M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling","created":"2026-03-15","cited_by_count":8,"area":null},{"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":"2606.01774","title":"FLARE: Diffusion for Hybrid Language Model","created":"2026-06-01","cited_by_count":6,"area":null},{"id":"2607.25357","title":"Raven: High-Recall Sequence Modeling with Sparse Memory Routing","created":"2026-07-28","cited_by_count":6,"area":null},{"id":"2609.20804","title":"An Empirical Study of Harness Design for Coding Agents","created":"2026-09-17","cited_by_count":6,"area":"agents"},{"id":"2602.10377","title":"Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs","created":"2026-02-10","cited_by_count":5,"area":"vla"},{"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":"2605.08301","title":"Priming: Hybrid State Space Models From Pre-trained Transformers","created":"2026-05-08","cited_by_count":5,"area":null},{"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":"2604.16279","title":"Evaluating the Progression of Large Language Model Capabilities for Small-Molecule Drug Design","created":"2026-04-17","cited_by_count":4,"area":null},{"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":"2606.26493","title":"Nemotron-Labs-TwoTower: Diffusion Language Modeling with Pretrained Autoregressive Context","created":"2026-06-25","cited_by_count":4,"area":"diffusion"},{"id":"2601.01972","title":"Hidden State Poisoning Attacks against Mamba-based Language Models","created":"2026-01-05","cited_by_count":2,"area":"ssm"},{"id":"2606.16774","title":"OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models","created":"2026-06-15","cited_by_count":2,"area":"agents"},{"id":"2610.13778","title":"ReplaySSM: Cache SSM Inputs, Not State","created":"2026-10-09","cited_by_count":2,"area":"inference"},{"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":"2603.23562","title":"Synthetic Mixed Training: Scaling Parametric Knowledge Acquisition Beyond RAG","created":"2026-03-24","cited_by_count":1,"area":null},{"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":"2605.20285","title":"Introspective X Training: Feedback Conditioning Improves Scaling Across all LLM Training Stages","created":"2026-05-19","cited_by_count":1,"area":"alignment"},{"id":"2606.12385","title":"Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs","created":"2026-06-10","cited_by_count":1,"area":null},{"id":"2607.04371","title":"Nemotron-Labs-3-Puzzle-75B-A9B: Compressing Hybrid MoE LLMs","created":"2026-07-05","cited_by_count":1,"area":"moe"},{"id":"2608.13482","title":"Synthetic Persona Pretraining: Alignment from Token Zero","created":"2026-08-13","cited_by_count":1,"area":null},{"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":"2603.06938","title":"Swimba: Switch Mamba Model Scales State Space Models","created":"2026-03-06","cited_by_count":0,"area":"moe"},{"id":"2604.02048","title":"Jagle: Building a Large-Scale Japanese Multimodal Post-Training Dataset for Vision-Language Models","created":"2026-04-02","cited_by_count":0,"area":"mllm"},{"id":"2604.11912","title":"How Transformers Learn to Plan via Multi-Token Prediction","created":"2026-04-13","cited_by_count":0,"area":null},{"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":"2605.20936","title":"DASH: Fast Differentiable Architecture Search for Hybrid Attention in Minutes on a Single GPU","created":"2026-05-20","cited_by_count":0,"area":"inference"},{"id":"2606.02867","title":"The Epi-LLM Framework: probing LLM behavioral priors through epidemiological agent-based models","created":"2026-06-01","cited_by_count":0,"area":"agents"},{"id":"2606.06622","title":"UnpredictaBench: A Benchmark for Evaluating Distributional Randomness in LLMs","created":"2026-06-04","cited_by_count":0,"area":null},{"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":"2607.28788","title":"EarlyDx: An Admission-Anchored Benchmark for Open-Ended Generation of Evidence-Supported ED-Encounter Diagnoses","created":"2026-07-30","cited_by_count":0,"area":null},{"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":"2608.28511","title":"Training Communication-Efficient Mixture-of-Experts Language Models with Layer Re-Configuration","created":"2026-08-28","cited_by_count":0,"area":"moe"},{"id":"2609.14422","title":"Safety Signals to Verify NetOps Agents with Action-Level Granularity","created":"2026-09-13","cited_by_count":0,"area":"agents"},{"id":"2609.15987","title":"Bellman Policy Optimization","created":"2026-09-14","cited_by_count":0,"area":"lr"},{"id":"2609.16540","title":"On the Importance of Gating: Memorization vs. In-Context Learning in State Space Models","created":"2026-09-15","cited_by_count":0,"area":null},{"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":"2609.33791","title":"Do We Really Need KL Divergence for On-Policy Distillation of Large Language Models?","created":"2026-09-27","cited_by_count":0,"area":"distill"},{"id":"2609.37852","title":"Delta-Matching: Closing the Final Gap of Native 8-bit Training for LLMs","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38530","title":"Shifting Mechanisms: How Positional Encoding Choice Shapes In-Context Retrieval","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.38712","title":"Staying on Task: Testing the Foundations of Long-Horizon Agent Reliability","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2609.38799","title":"Overlap, Unique and Conflict: Can LLMs Extract What They Can Recognize?","created":"2026-09-30","cited_by_count":0,"area":null},{"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":"2609.39076","title":"Multi-LLM Collaborative Alignment via Stackelberg Games","created":"2026-09-30","cited_by_count":0,"area":"alignment"},{"id":"2609.39661","title":"The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.40285","title":"PivotOPD: Learning to Recover from Pivotal Mistakes in Multi-Turn Agents","created":"2026-09-30","cited_by_count":0,"area":"distill"},{"id":"2610.17018","title":"LLM Evaluation is a Forecasting Problem","created":"2026-10-12","cited_by_count":0,"area":null},{"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"},{"id":"2610.19367","title":"Beyond Corrected Actions: Training LLM Agents on Textual Critiques","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}