{"total":55,"rows":[{"id":"2603.20633","title":"Seed1.8 Model Card: Towards Generalized Real-World Agency","created":"2026-03-21","cited_by_count":50,"area":null},{"id":"2512.13607","title":"Nemotron-Cascade: Scaling Cascaded Reinforcement Learning for General-Purpose Reasoning Models","created":"2025-12-15","cited_by_count":48,"area":"lr"},{"id":"2602.16763","title":"When AI Benchmarks Plateau: A Systematic Study of Benchmark Saturation","created":"2026-02-18","cited_by_count":33,"area":null},{"id":"2508.18993","title":"GitTaskBench: A Benchmark for Code Agents Solving Real-World Tasks Through Code Repository Leveraging","created":"2025-08-26","cited_by_count":25,"area":"agents"},{"id":"2509.21016","title":"RL Grokking Recipe: How Does RL Unlock and Transfer New Algorithms in LLMs?","created":"2025-09-25","cited_by_count":23,"area":null},{"id":"2512.15699","title":"FrontierCS: Evolving Challenges for Evolving Intelligence","created":"2025-12-17","cited_by_count":23,"area":null},{"id":"2602.06176","title":"Large Language Model Reasoning Failures","created":"2026-02-05","cited_by_count":21,"area":"lr"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2512.04111","title":"CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding","created":"2025-11-30","cited_by_count":12,"area":"agents"},{"id":"2507.20439","title":"When Prompts Go Wrong: Evaluating Code Model Robustness to Ambiguous, Contradictory, and Incomplete Task Descriptions","created":"2025-07-27","cited_by_count":11,"area":null},{"id":"2510.12803","title":"AutoCode: LLMs as Problem Setters for Competitive Programming","created":"2025-09-29","cited_by_count":11,"area":null},{"id":"2512.10398","title":"Confucius Code Agent: Scalable Agent Scaffolding for Real-World Codebases","created":"2025-12-11","cited_by_count":11,"area":"agents"},{"id":"2604.14164","title":"How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data","created":"2026-03-23","cited_by_count":8,"area":"lr"},{"id":"2506.18504","title":"Generalizing vision-language models to novel domains: A comprehensive survey","created":"2025-06-23","cited_by_count":7,"area":"mllm"},{"id":"2602.04254","title":"Scaling Agentic Verifier for Competitive Coding","created":"2026-02-04","cited_by_count":7,"area":"agents"},{"id":"2602.13367","title":"Nanbeige4.1-3B: A Small General Model that Reasons, Aligns, and Acts","created":"2026-02-13","cited_by_count":6,"area":"lr"},{"id":"2510.00332","title":"When Hallucination Costs Millions: Benchmarking AI Agents in High-Stakes Adversarial Financial Markets","created":"2025-09-30","cited_by_count":5,"area":null},{"id":"2510.09595","title":"LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?","created":"2025-10-10","cited_by_count":4,"area":null},{"id":"2606.21228","title":"Sakana Fugu Technical Report","created":"2026-06-19","cited_by_count":4,"area":"agents"},{"id":"2511.16205","title":"ChemLabs on ChemO: A Multi-Agent System for Multimodal Reasoning on IChO 2025","created":"2025-11-20","cited_by_count":3,"area":"lr"},{"id":"2602.06319","title":"Exposing Weaknesses of Large Reasoning Models through Graph Algorithm Problems","created":"2026-02-06","cited_by_count":3,"area":"lr"},{"id":"2605.15177","title":"OpenDeepThink: Parallel Reasoning via Bradley-Terry Aggregation","created":"2026-05-14","cited_by_count":3,"area":"lr"},{"id":"2605.24693","title":"CP-Agent: A Calibrated Risk-Controlled Agent for Feedback-Driven Competitive Programming","created":"2026-05-23","cited_by_count":3,"area":"agents"},{"id":"2607.19653","title":"PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2510.07315","title":"SWE-IF: Aligning Code Evaluation with Human Preference","created":"2025-10-08","cited_by_count":2,"area":"alignment"},{"id":"2510.16259","title":"Distractor Injection Attacks on Large Reasoning Models: Characterization and Defense","created":"2025-10-17","cited_by_count":2,"area":"lr"},{"id":"2601.01739","title":"K-EXAONE Technical Report","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2603.15921","title":"VIBEPASS: Can Vibe Coders Really Pass the Vibe Check?","created":"2026-03-16","cited_by_count":2,"area":"agents"},{"id":"2604.10182","title":"Credit-Budgeted ICPC-Style Coding: When Agents Must Pay for Every Decision","created":"2026-04-11","cited_by_count":2,"area":"agents"},{"id":"2605.16358","title":"LEAF: A Living Benchmark for Event-Augmented Forecasting","created":"2026-05-09","cited_by_count":2,"area":null},{"id":"2606.12864","title":"Beyond Problem Solving: UOJ-Bench for Evaluating Code Generation, Hacking, and Repair in Competitive Programming","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2606.20517","title":"Multi-LCB: Extending LiveCodeBench to Multiple Programming Languages","created":"2026-06-18","cited_by_count":2,"area":null},{"id":"2606.31182","title":"AI-Assisted Discovery of Convex Relaxations via Dual Agents","created":"2026-06-30","cited_by_count":2,"area":"agents"},{"id":"2608.01684","title":"GABench: A Comprehensive Benchmark for Evaluating LLM Agents on Graph Analysis Tasks","created":"2026-08-03","cited_by_count":2,"area":"agents"},{"id":"2510.17868","title":"UniCode: Augmenting Evaluation for Code Reasoning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2510.22340","title":"DynaSolidGeo: A Dynamic Benchmark for Genuine Spatial Mathematical Reasoning of VLMs in Solid Geometry","created":"2025-10-25","cited_by_count":1,"area":"lr"},{"id":"2511.15355","title":"HEAD-QA v2: Expanding a Healthcare Benchmark for Reasoning","created":"2025-11-19","cited_by_count":1,"area":"lr"},{"id":"2601.04996","title":"AlgBench: To What Extent Do Large Reasoning Models Understand Algorithms?","created":"2026-01-08","cited_by_count":1,"area":"lr"},{"id":"2602.02523","title":"TabularMath: Evaluating Computational Extrapolation in Tabular Learning via Program-Verified Synthesis","created":"2026-01-25","cited_by_count":1,"area":null},{"id":"2604.21916","title":"MathDuels: A Self-Play Benchmark That Grows","created":"2026-04-23","cited_by_count":1,"area":"synth"},{"id":"2605.07806","title":"Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs","created":"2026-05-08","cited_by_count":1,"area":"lr"},{"id":"2605.15607","title":"Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language","created":"2026-05-15","cited_by_count":1,"area":null},{"id":"2605.19782","title":"Prior Knowledge or Search? A Study of LLM Agents in Hardware-Aware Code Optimization","created":"2026-05-19","cited_by_count":1,"area":"agents"},{"id":"2606.32007","title":"AxDafny: Agentic Verified Code Generation in Dafny","created":"2026-06-30","cited_by_count":1,"area":"agents"},{"id":"2609.15983","title":"Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer Science","created":"2026-09-14","cited_by_count":1,"area":"agents"},{"id":"2510.27628","title":"Validity Is What You Need","created":"2025-10-31","cited_by_count":0,"area":"agents"},{"id":"2512.21010","title":"LLM Swiss Round: Aggregating Multi-Benchmark Performance via Competitive Swiss-System Dynamics","created":"2025-12-24","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":"2605.05949","title":"MAS-Algorithm: A Workflow for Solving Algorithmic Programming Problems with a Multi-Agent System","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.25450","title":"The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms","created":"2026-06-24","cited_by_count":0,"area":null},{"id":"2608.16033","title":"$R^3$-Bench: LLMs Struggle with Resource-Rational Reasoning under Shared Budgets","created":"2026-08-17","cited_by_count":0,"area":"lr"},{"id":"2608.29632","title":"InteractBench: Benchmarking LLMs on Competitive Programming under Unrevealed Information","created":"2026-08-30","cited_by_count":0,"area":"lr"},{"id":"2609.00058","title":"CUDA-Harness: Harnessing Agentic CUDA Kernel Generation and Optimization from Natural Language","created":"2026-08-30","cited_by_count":0,"area":"agents"},{"id":"2609.29410","title":"Large Language Models for Programming: Actually Fixing or Reimplementing Incorrect Code?","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2610.19433","title":"EvoProbe: Evaluation-Driven Benchmark Evolution for LLM Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}