{"total":42,"rows":[{"id":"2509.17765","title":"Qwen3-Omni Technical Report","created":"2025-09-22","cited_by_count":497,"area":null},{"id":"2505.24760","title":"REASONING GYM: Reasoning Environments for Reinforcement Learning with Verifiable Rewards","created":"2025-05-30","cited_by_count":130,"area":null},{"id":"2510.06265","title":"Large Language Models Hallucination: A Comprehensive Survey","created":"2025-10-05","cited_by_count":49,"area":null},{"id":"2509.16679","title":"Reinforcement Learning Meets Large Language Models: A Survey of Advancements and Applications Across the LLM Lifecycle","created":"2025-09-20","cited_by_count":35,"area":null},{"id":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22,"area":null},{"id":"2504.21303","title":"Confidence in Large Language Model Evaluation: A Bayesian Approach to Limited-Sample Challenges","created":"2025-04-30","cited_by_count":8,"area":null},{"id":"2602.12413","title":"Soft Contamination Means Benchmarks Test Shallow Generalization","created":"2026-02-12","cited_by_count":8,"area":null},{"id":"2510.01143","title":"Generalized Parallel Scaling with Interdependent Generations","created":"2025-10-01","cited_by_count":6,"area":null},{"id":"2602.05843","title":"OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions","created":"2026-02-05","cited_by_count":6,"area":null},{"id":"2601.19924","title":"OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity Scaling","created":"2026-01-09","cited_by_count":5,"area":null},{"id":"2606.25178","title":"Transferability for General Reasoning: An Automated Curriculum for Multi-Domain RLVR","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2511.07464","title":"Motif 2 12.7B technical report","created":"2025-11-07","cited_by_count":4,"area":null},{"id":"2602.10718","title":"SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining","created":"2026-02-11","cited_by_count":4,"area":null},{"id":"2505.14763","title":"Unifying Inference-Time Planning Language Generation","created":"2025-05-20","cited_by_count":3,"area":null},{"id":"2510.05486","title":"Language Model as Planner and Formalizer under Constraints","created":"2025-10-07","cited_by_count":3,"area":null},{"id":"2510.14581","title":"Model-agnostic Selective Labeling with Provable Statistical Guarantees","created":"2025-10-16","cited_by_count":3,"area":null},{"id":"2604.03616","title":"The Format Tax","created":"2026-04-04","cited_by_count":3,"area":null},{"id":"2605.11167","title":"The Bicameral Model: Bidirectional Hidden-State Coupling Between Parallel Language Models","created":"2026-05-11","cited_by_count":2,"area":null},{"id":"2609.06107","title":"DataFlex-RL: An Evaluation Platform for RLVR Data Policies","created":"2026-09-05","cited_by_count":2,"area":null},{"id":"2510.00777","title":"In-Place Feedback: Reliable Refinement for Multi-Turn Expert-LLM Collaboration","created":"2025-10-01","cited_by_count":1,"area":null},{"id":"2511.19872","title":"Simulated Self-Assessment in Large Language Models: A Psychometric Approach to AI Self-Efficacy","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2608.00991","title":"SCHEDBench: A Benchmark for Evaluating LLM Constraint Faithfulness in Natural-Language Combinatorial Scheduling","created":"2026-08-02","cited_by_count":1,"area":null},{"id":"2508.20978","title":"Scaling Neuro-symbolic Problem Solving: Solver-Free Learning of Constraints and Objectives","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2509.02225","title":"Towards Fundamental Language Models: Does Linguistic Competence Scale with Model Size?","created":"2025-09-02","cited_by_count":0,"area":null},{"id":"2601.22345","title":"Failing to Explore: Language Models on Interactive Tasks","created":"2026-01-29","cited_by_count":0,"area":null},{"id":"2602.11674","title":"Benchmark Health Index: A Systematic Framework for Benchmarking the Benchmarks of LLMs","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2604.20523","title":"Early-Stage Product Line Validation Using LLMs: A Study on Semi-Formal Blueprint Analysis","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2605.05741","title":"HyperLens: Quantifying Cognitive Effort in LLMs with Fine-grained Confidence Trajectory","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.08905","title":"Forge: Quality-Aware Reinforcement Learning for NP-Hard Optimization in LLMs","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2606.10722","title":"Continual LLM Upcycling: A Predictor-Gated Bank-Wise Sparsity Training Recipe for Dense-to-Sparse LLMs","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.26671","title":"NebulaExp-8B: An Empirical Post-Training Pipeline via Full-Scale Ablation Research","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2608.04397","title":"NOLLI: A Difficulty-Calibrated Puzzle Benchmark for Diagnosing the English-Korean Performance Gap","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2608.05148","title":"Reasoning Core: Designing Broad Procedural Data for Completion-Supervised Reasoning Training","created":"2026-08-05","cited_by_count":0,"area":null},{"id":"2609.00062","title":"RePro: Proof-Verified Benchmark Rewriting for Reliable Evaluation of LLM Mathematical Problem Solving","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.09081","title":"Everything in Moderation: Per-Domain Coverage Optima and Alignment-Resistant Domain Gaps in Multi-Domain Mid-Training","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.27517","title":"Not What You Meant: Can LLMs Follow a Specified Negation Semantics?","created":"2026-09-23","cited_by_count":0,"area":null},{"id":"2609.34864","title":"On the Limits of Metacognitive Monitoring in LLMs","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36860","title":"IronLLM: Forging Compact Edge-Native Language Models for Real-Time Embodied Intelligence","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.00928","title":"Efficient Task Adaptation in Large Language Models: A Survey of Weight-Based, Prompt-Based, and Embedding-Based Adaptations","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.02632","title":"Online Verification of Language Model Responses Under Cost Constraints","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.06329","title":"Dynamic Minimax Regret Optimization for Robust LLM Post-Training","created":"2026-10-05","cited_by_count":0,"area":null},{"id":"2610.14021","title":"CoEvoke: Evoking Multi-Agent Collaboration for Trajectory Collection","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}