{"total":94,"rows":[{"id":"2606.19348","title":"DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligence","created":"2026-04-26","cited_by_count":1040,"area":"moe"},{"id":"2605.00674","title":"Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs","created":"2026-05-01","cited_by_count":137,"area":null},{"id":"2512.17260","title":"Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experience","created":"2025-12-19","cited_by_count":44,"area":null},{"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":"2601.16725","title":"LongCat-Flash-Thinking-2601 Technical Report","created":"2026-01-23","cited_by_count":34,"area":"lr"},{"id":"2602.03442","title":"A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces","created":"2026-02-03","cited_by_count":24,"area":"lr"},{"id":"2602.07594","title":"Learning to Self-Verify Makes Language Models Better Reasoners","created":"2026-02-07","cited_by_count":21,"area":"lr"},{"id":"2601.02872","title":"LongBench Pro: A More Realistic and Comprehensive Bilingual Long-Context Evaluation Benchmark","created":"2026-01-06","cited_by_count":19,"area":null},{"id":"2602.03619","title":"Learning Query-Specific Rubrics from Human Preferences for DeepResearch Report Generation","created":"2026-02-03","cited_by_count":18,"area":"alignment"},{"id":"2601.14209","title":"InT: Self-Proposed Interventions Enable Credit Assignment in LLM Reasoning","created":"2026-01-20","cited_by_count":14,"area":"lr"},{"id":"2604.26256","title":"DORA: A Scalable Asynchronous Reinforcement Learning System for Language Model Training","created":"2026-04-29","cited_by_count":14,"area":null},{"id":"2602.03773","title":"Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL","created":"2026-02-03","cited_by_count":12,"area":"lr"},{"id":"2601.07349","title":"Reward Modeling from Natural Language Human Feedback","created":"2026-01-12","cited_by_count":11,"area":"alignment"},{"id":"2602.04649","title":"Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models","created":"2026-02-04","cited_by_count":11,"area":"lr"},{"id":"2602.08711","title":"TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions","created":"2026-02-09","cited_by_count":11,"area":null},{"id":"2512.24618","title":"Youtu-LLM: Unlocking the Native Agentic Potential for Lightweight Large Language Models","created":"2025-12-31","cited_by_count":10,"area":"agents"},{"id":"2602.02244","title":"Entropy-Preserving Supervised Fine-Tuning via Adaptive Self-Distillation for Large Reasoning Models","created":"2026-02-02","cited_by_count":9,"area":"lr"},{"id":"2602.16793","title":"Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Models","created":"2026-02-18","cited_by_count":9,"area":"lr"},{"id":"2604.06802","title":"Riemann-Bench: A Benchmark for Moonshot Mathematics","created":"2026-04-08","cited_by_count":8,"area":null},{"id":"2601.04525","title":"GRACE: Reinforcement Learning for Grounded Response and Abstention under Contextual Evidence","created":"2026-01-08","cited_by_count":7,"area":"lr"},{"id":"2601.10306","title":"Evidence-Augmented Policy Optimization with Reward Co-Evolution for Long-Context Reasoning","created":"2026-01-15","cited_by_count":7,"area":"lr"},{"id":"2604.22074","title":"Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning","created":"2026-04-23","cited_by_count":7,"area":"lr"},{"id":"2601.21464","title":"Conversation for Non-verifiable Learning: Self-Evolving LLMs through Meta-Evaluation","created":"2026-01-29","cited_by_count":6,"area":"synth"},{"id":"2602.03053","title":"MAS-ProVe: Understanding the Process Verification of Multi-Agent Systems","created":"2026-02-03","cited_by_count":6,"area":"lr"},{"id":"2604.18584","title":"MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrieval","created":"2026-04-20","cited_by_count":6,"area":"lr"},{"id":"2602.08498","title":"Characterizing, Evaluating, and Optimizing Complex Reasoning","created":"2026-02-09","cited_by_count":5,"area":"lr"},{"id":"2604.24198","title":"Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis","created":"2026-04-27","cited_by_count":5,"area":"lr"},{"id":"2607.11172","title":"STAMP: Provenance-Guided Credit Assignment for Deep Search Agents","created":"2026-07-13","cited_by_count":5,"area":null},{"id":"2608.31075","title":"Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence","created":"2026-08-31","cited_by_count":5,"area":"lr"},{"id":"2512.09443","title":"A Human-AI Collaborative Workflow for Mathematical Discovery: A Case Study in Grover-Compatible Riemannian Optimization","created":"2025-12-10","cited_by_count":4,"area":null},{"id":"2604.05868","title":"Understanding Performance Gap Between Parallel and Sequential Sampling in Large Reasoning Models","created":"2026-04-07","cited_by_count":4,"area":"lr"},{"id":"2605.12519","title":"Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models","created":"2026-04-03","cited_by_count":4,"area":"lr"},{"id":"2605.20531","title":"Pseudo-Formalization for Automatic Proof Verification","created":"2026-05-19","cited_by_count":4,"area":"lr"},{"id":"2606.08625","title":"From Holistic Evaluation to Structured Criteria: Rubrics Across the Evolving LLM Landscape","created":"2026-06-07","cited_by_count":4,"area":null},{"id":"2602.21228","title":"ImpRIF: Stronger Implicit Reasoning Leads to Better Complex Instruction Following","created":"2026-02-04","cited_by_count":3,"area":"lr"},{"id":"2603.03379","title":"MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning","created":"2026-03-03","cited_by_count":3,"area":"lr"},{"id":"2603.03538","title":"Verify to Amplify: Improving Reasoning via Learned Chain-of-Thought Verification","created":"2026-03-03","cited_by_count":3,"area":"lr"},{"id":"2603.18886","title":"Reasoning over mathematical objects: on-policy reward modeling and test time aggregation","created":"2026-03-19","cited_by_count":3,"area":"lr"},{"id":"2604.01161","title":"Reasoning Shift: How Context Silently Shortens LLM Reasoning","created":"2026-04-01","cited_by_count":3,"area":"lr"},{"id":"2604.04898","title":"QED-Nano: Teaching a Tiny Model to Prove Hard Theorems","created":"2026-04-06","cited_by_count":3,"area":null},{"id":"2606.15532","title":"EIBench: A Simulator-Based Benchmark and Turn-Credit RL for Emotion Management","created":"2026-06-14","cited_by_count":3,"area":"lr"},{"id":"2606.31575","title":"Which Tokens Matter? Adaptive Token Selection for RLVR with the Relative Surprisal Index","created":"2026-06-30","cited_by_count":3,"area":"lr"},{"id":"2603.13309","title":"Preventing Curriculum Collapse in Self-Evolving Reasoning Systems","created":"2026-03-03","cited_by_count":2,"area":"lr"},{"id":"2603.21574","title":"Adaptive Robust Estimator for Multi-Agent Reinforcement Learning","created":"2026-03-23","cited_by_count":2,"area":"lr"},{"id":"2605.28805","title":"OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration","created":"2026-05-27","cited_by_count":2,"area":"mllm"},{"id":"2605.30290","title":"Self-Trained Verification for Training- and Test-Time Self-Improvement","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2606.03660","title":"From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models","created":"2026-06-02","cited_by_count":2,"area":"lr"},{"id":"2606.12360","title":"Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2606.21943","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","created":"2026-06-20","cited_by_count":2,"area":"lr"},{"id":"2606.24892","title":"ReviewGuard: Aligning LLM-Assisted Peer Review with Long-Term Scientific Impact","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2607.02959","title":"Incentivizing Vision Language Models to Search for Long Video Question Answering","created":"2026-07-03","cited_by_count":2,"area":"mllm"},{"id":"2607.04179","title":"CritiqueDriveVLM: From Verifier-Guided Reinforcement Learning to Latent Thought Distillation for Autonomous Driving","created":"2026-07-05","cited_by_count":2,"area":"lr"},{"id":"2608.12004","title":"RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks","created":"2026-08-12","cited_by_count":2,"area":null},{"id":"2608.16977","title":"The Problem Is the Problem: Towards Scalable Mathematical Discovery","created":"2026-08-17","cited_by_count":2,"area":null},{"id":"2609.19101","title":"Monitoring and Discovering Reward Hacking with Internal Representations during LLM Evaluations","created":"2026-09-16","cited_by_count":2,"area":"alignment"},{"id":"2601.18771","title":"Dep-Search: Learning Dependency-Aware Reasoning Traces with Persistent Memory","created":"2026-01-26","cited_by_count":1,"area":"lr"},{"id":"2602.10609","title":"Online Causal Kalman Filtering for Stable and Effective Policy Optimization","created":"2026-02-11","cited_by_count":1,"area":null},{"id":"2603.22363","title":"Early Discoveries of Algorithmist I: Promise of Provable Algorithm Synthesis at Scale","created":"2026-03-23","cited_by_count":1,"area":"lr"},{"id":"2604.01302","title":"Scaling Reasoning Tokens via RL and Parallel Thinking: Evidence From Competitive Programming","created":"2026-04-01","cited_by_count":1,"area":"lr"},{"id":"2605.10344","title":"TMAS: Scaling Test-Time Compute via Multi-Agent Synergy","created":"2026-05-11","cited_by_count":1,"area":"lr"},{"id":"2605.19338","title":"STAR-P\\'olyaMath: Multi-Agent Reasoning under Persistent Meta-Strategic Supervision","created":"2026-05-19","cited_by_count":1,"area":"lr"},{"id":"2605.27881","title":"Retrieval, Reward, and Training Protocols: What Matters in Training Search Agents?","created":"2026-05-27","cited_by_count":1,"area":"agents"},{"id":"2606.00660","title":"FineVerify: Scaling Test-Time Compute with Fine-Grained Self-Verification for Agentic Search","created":"2026-05-30","cited_by_count":1,"area":"lr"},{"id":"2606.20740","title":"VeriBound: PAC-Bayesian Generalization Bounds for Process Reward Models Trained with Formal Verification Tools","created":"2026-06-17","cited_by_count":1,"area":"lr"},{"id":"2609.25831","title":"Sometimes You Gotta Run Before You Can Walk: Run-then-Walk Scheduling Strategy for VLM Autonomous Driving","created":"2026-09-22","cited_by_count":1,"area":"driving"},{"id":"2512.13764","title":"Mathematics and Coding are Universal AI Benchmarks","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2512.14761","title":"CAPE: Capability Achievement via Policy Execution","created":"2025-12-15","cited_by_count":0,"area":null},{"id":"2512.19728","title":"Hard Negative Sample-Augmented DPO Post-Training for Small Language Models","created":"2025-12-17","cited_by_count":0,"area":"lr"},{"id":"2601.10318","title":"Boundary-Aware NL2SQL: Integrating Reliability through Hybrid Reward and Data Synthesis","created":"2026-01-15","cited_by_count":0,"area":"synth"},{"id":"2602.08708","title":"Intermediate Results on the Complexity of STRIPS$_{1}^{1}$","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2603.05120","title":"Bidirectional Curriculum Generation: A Multi-Agent Framework for Data-Efficient Mathematical Reasoning","created":"2026-03-05","cited_by_count":0,"area":"lr"},{"id":"2604.10110","title":"Trust Your Memory: Verifiable Control of Smart Homes through Reinforcement Learning with Multi-dimensional Rewards","created":"2026-04-11","cited_by_count":0,"area":"lr"},{"id":"2605.05711","title":"Closing the Loop: Unified 3D Scene Generation and Immersive Interaction via LLM-RL Coupling","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.28109","title":"Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2605.28389","title":"FABSVer: Faster Training and Better Self-Verification for LLM Mathematical Reasoning","created":"2026-05-27","cited_by_count":0,"area":"lr"},{"id":"2606.04648","title":"BiNSGPS: Geometry Problem Solving via Bidirectional Neuro-Symbolic Interaction","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2606.09380","title":"Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short","created":"2026-06-08","cited_by_count":0,"area":"lr"},{"id":"2606.10479","title":"ComBench: A Benchmark for Rigorous Proof Reasoning and Constructive Realization in Olympiad-Level Combinatorics","created":"2026-06-09","cited_by_count":0,"area":"lr"},{"id":"2606.15258","title":"Mask-Proof: An LLM-based Automated Data Curation Pipeline on Mathematical Proofs","created":"2026-06-13","cited_by_count":0,"area":null},{"id":"2606.18961","title":"Be Your Own Teacher: Steering Protein Language Models via Unsupervised Reward Optimization","created":"2026-06-17","cited_by_count":0,"area":"alignment"},{"id":"2607.06820","title":"Evaluating SageMath-Augmented LLM Agents for Computational and Experimental Mathematics","created":"2026-07-07","cited_by_count":0,"area":"agents"},{"id":"2608.23719","title":"ADE: Agentic Data Evolution Framework for Human-Centered Objectives","created":"2026-08-24","cited_by_count":0,"area":"agents"},{"id":"2608.30181","title":"A.X K2 Technical Report","created":"2026-08-31","cited_by_count":0,"area":"agents"},{"id":"2609.05988","title":"DART: Distributional Adversarial Recurrent Training for Algorithm Learning","created":"2026-09-05","cited_by_count":0,"area":"lr"},{"id":"2609.10712","title":"An Open Recipe for IMO Gold: Training Nemotron for Olympiad Mathematics","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.11018","title":"Defining AI Agents: A Compendium of Criteria, Metrics, and Benchmarks","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.19156","title":"Reflective Recovery: A Self-Supervised Method for Reasoning by Learning from Mistakes","created":"2026-07-24","cited_by_count":0,"area":"lr"},{"id":"2609.35701","title":"MeqMuon: Matrix-Equilibrating Muon for LLM Pretraining","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36914","title":"Can Language Models Learn to Forecast Stock Prices","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2609.38332","title":"Hermes: Learning Contextual Reasoning Unlocks Test-Time Scaling","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.08561","title":"Reinforcement Learning for Hierarchical Reasoning Rewards: Minimax-Optimal Rates with Transformers","created":"2026-10-06","cited_by_count":0,"area":"lr"},{"id":"2610.13058","title":"Travel Back To Move Forward: Retrospective Exploration and Evolving for Long Horizon Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.13996","title":"Splicing Hints into Reasoning Traces: Learning from Demonstrator Failures","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2610.17697","title":"LeanPRM: Lean-Grounded Process Supervision for Natural Language Proof Verification","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}