{"total":98,"rows":[{"id":"2503.09567","title":"Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models","created":"2025-03-12","cited_by_count":384,"area":"lr"},{"id":"2509.25140","title":"ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory","created":"2025-09-29","cited_by_count":284,"area":"lr"},{"id":"2503.24235","title":"A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?","created":"2025-03-31","cited_by_count":223,"area":"lr"},{"id":"2507.23370","title":"Trae Agent: An LLM-based Agent for Software Engineering with Test-time Scaling","created":"2025-07-31","cited_by_count":94,"area":"lr"},{"id":"2506.17811","title":"RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Models","created":"2025-06-21","cited_by_count":61,"area":"vla"},{"id":"2504.15466","title":"Learning Adaptive Parallel Reasoning with Language Models","created":"2025-04-21","cited_by_count":58,"area":"lr"},{"id":"2506.03136","title":"Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning","created":"2025-06-03","cited_by_count":56,"area":null},{"id":"2505.11484","title":"SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning","created":"2025-05-16","cited_by_count":41,"area":"lr"},{"id":"2505.24863","title":"AlphaOne: Reasoning Models Thinking Slow and Fast at Test Time","created":"2025-05-30","cited_by_count":29,"area":"lr"},{"id":"2602.02488","title":"RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System","created":"2026-02-02","cited_by_count":24,"area":"agents"},{"id":"2506.05566","title":"ScaleRTL: Scaling LLMs with Reasoning Data and Test-Time Compute for Accurate RTL Code Generation","created":"2025-06-05","cited_by_count":22,"area":"lr"},{"id":"2504.05408","title":"Frontier AI's Impact on the Cybersecurity Landscape","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2503.18809","title":"Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code","created":"2025-03-24","cited_by_count":18,"area":null},{"id":"2506.08311","title":"Understanding Automated Program Repair Agents Through the Lens of Traceability: An Empirical Study","created":"2025-06-10","cited_by_count":16,"area":"agents"},{"id":"2504.13828","title":"Generative AI Act II: Test Time Scaling Drives Cognition Engineering","created":"2025-04-18","cited_by_count":15,"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":"2508.09670","title":"MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement","created":"2025-08-13","cited_by_count":14,"area":"lr"},{"id":"2508.10874","title":"SSRL: Self-Search Reinforcement Learning","created":"2025-08-14","cited_by_count":14,"area":"lr"},{"id":"2505.17653","title":"GeoGramBench: Benchmarking the Geometric Program Reasoning in Modern LLMs","created":"2025-05-23","cited_by_count":13,"area":"lr"},{"id":"2505.18955","title":"Co-PatcheR: Collaborative Software Patching with Component(s)-specific Small Reasoning Models","created":"2025-05-25","cited_by_count":12,"area":"lr"},{"id":"2603.04304","title":"$V_1$: Unifying Generation and Self-Verification for Parallel Reasoners","created":"2026-03-04","cited_by_count":12,"area":"lr"},{"id":"2503.18069","title":"Long Is More Important Than Difficult for Training Reasoning Models","created":"2025-03-23","cited_by_count":11,"area":"lr"},{"id":"2506.05745","title":"SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models","created":"2025-06-06","cited_by_count":10,"area":"lr"},{"id":"2505.18149","title":"First Finish Search: Efficient Test-Time Scaling in Large Language Models","created":"2025-05-23","cited_by_count":9,"area":"lr"},{"id":"2507.20187","title":"Diversity-Enhanced Reasoning for Subjective Questions","created":"2025-07-27","cited_by_count":9,"area":"lr"},{"id":"2605.01194","title":"VLA-ATTC: Adaptive Test-Time Compute for VLA Models with Relative Action Critic Model","created":"2026-05-02","cited_by_count":9,"area":"lr"},{"id":"2507.17307","title":"R-Stitch: Dynamic Trajectory Stitching for Efficient Reasoning","created":"2025-07-23","cited_by_count":7,"area":"lr"},{"id":"2601.19697","title":"AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion","created":"2026-01-27","cited_by_count":7,"area":null},{"id":"2506.00400","title":"Scaling Textual Gradients via Sampling-Based Momentum","created":"2025-05-31","cited_by_count":6,"area":null},{"id":"2511.16858","title":"Investigating Test Overfitting on SWE-bench","created":"2025-11-20","cited_by_count":6,"area":null},{"id":"2510.06471","title":"Test-Time Scaling of Reasoning Models for Machine Translation","created":"2025-10-07","cited_by_count":5,"area":"lr"},{"id":"2602.17684","title":"CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models","created":"2026-02-04","cited_by_count":5,"area":"alignment"},{"id":"2603.15707","title":"SEMAG: Self-Evolutionary Multi-Agent Code Generation","created":"2026-03-16","cited_by_count":5,"area":"agents"},{"id":"2607.00990","title":"SWE-Doctor: Guiding Software Engineering Agents with Runtime Diagnosis from Multi-Faceted Bug Reproduction Tests","created":"2026-07-01","cited_by_count":5,"area":"agents"},{"id":"2505.15340","title":"SSR: Speculative Parallel Scaling Reasoning in Test-time","created":"2025-05-21","cited_by_count":4,"area":"lr"},{"id":"2506.06052","title":"DCP-Bench-Open: Evaluating LLMs for Constraint Modelling of Discrete Combinatorial Problems","created":"2025-06-06","cited_by_count":4,"area":null},{"id":"2506.13932","title":"Code Reasoning for Software Engineering Tasks: A Survey and A Call to Action","created":"2025-06-16","cited_by_count":4,"area":"lr"},{"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":"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":"2506.00845","title":"Generalizable LLM Learning of Graph Synthetic Data with Post-training Alignment","created":"2025-06-01","cited_by_count":3,"area":"lr"},{"id":"2509.15148","title":"ATTS: Asynchronous Test-Time Scaling via Conformal Prediction","created":"2025-09-18","cited_by_count":3,"area":"lr"},{"id":"2509.25987","title":"R-Log: Incentivizing Log Analysis Capability in LLMs via Reasoning-based Reinforcement Learning","created":"2025-09-30","cited_by_count":3,"area":"lr"},{"id":"2511.16005","title":"InfCode-C++: Intent-Guided Semantic Retrieval and AST-Structured Search for C++ Issue Resolution","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2512.14917","title":"Evaluating Code Reasoning Abilities of Large Language Models Under Real-World Settings","created":"2025-12-16","cited_by_count":3,"area":"lr"},{"id":"2601.20615","title":"DRAINCODE: Stealthy Energy Consumption Attacks on Retrieval-Augmented Code Generation via Context Poisoning","created":"2026-01-28","cited_by_count":3,"area":"rag"},{"id":"2601.22249","title":"FunPRM: Function-as-Step Process Reward Model with Meta Reward Correction for Code Generation","created":"2026-01-29","cited_by_count":3,"area":"lr"},{"id":"2602.06098","title":"A Theoretical Analysis of Test-Driven Code Generation","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2603.27448","title":"GIFT: Bootstrapping Image-to-CAD Program Synthesis via Geometric Feedback","created":"2026-03-28","cited_by_count":3,"area":null},{"id":"2605.15669","title":"Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test Generation","created":"2026-05-15","cited_by_count":3,"area":"agents"},{"id":"2606.18247","title":"Visual Verification Enables Inference-time Steering and Autonomous Policy Improvement","created":"2026-06-16","cited_by_count":3,"area":"vla"},{"id":"2509.25420","title":"Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search","created":"2025-09-29","cited_by_count":2,"area":"lr"},{"id":"2511.00521","title":"Reasoning Planning for Language Models","created":"2025-11-01","cited_by_count":2,"area":"lr"},{"id":"2602.05242","title":"EGSS: Entropy-guided Stepwise Scaling for Reliable Software Engineering","created":"2026-02-05","cited_by_count":2,"area":"lr"},{"id":"2603.12149","title":"Linking Perception, Confidence and Accuracy in MLLMs","created":"2026-03-12","cited_by_count":2,"area":"mllm"},{"id":"2604.00790","title":"RefineRL: Advancing Competitive Programming with Self-Refinement Reinforcement Learning","created":"2026-04-01","cited_by_count":2,"area":"lr"},{"id":"2604.03922","title":"ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation","created":"2026-04-05","cited_by_count":2,"area":null},{"id":"2604.16995","title":"SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models","created":"2026-04-18","cited_by_count":2,"area":null},{"id":"2605.17626","title":"Verifier-Guided Code Translation via Meta-Step Decoding","created":"2026-05-17","cited_by_count":2,"area":"lr"},{"id":"2607.18859","title":"PhoenixRepair: Rethinking Repair Strategy Exploration in Software Agents","created":"2026-07-21","cited_by_count":2,"area":"lr"},{"id":"2608.23848","title":"Exploit More, Explore Smarter for Budget-Constrained Agentic Search","created":"2026-08-24","cited_by_count":2,"area":"agents"},{"id":"2505.13553","title":"Towards Functional Correctness of Large Code Models with Selective Generation","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2508.17250","title":"Routing Distilled Knowledge via Mixture of LoRA Experts for Large Language Model based Bundle Generation","created":"2025-08-24","cited_by_count":1,"area":"distill"},{"id":"2510.00501","title":"CodeChemist: Test-Time Scaling for Low-Resource Code Generation via Functional Knowledge Transfer","created":"2025-10-01","cited_by_count":1,"area":"lr"},{"id":"2510.06014","title":"ARISE: An Adaptive Resolution-Aware Metric for Test-Time Scaling Evaluation in Large Reasoning Models","created":"2025-10-07","cited_by_count":1,"area":"lr"},{"id":"2510.21604","title":"RETuning: Upgrading Inference-Time Scaling for Stock Movement Prediction with Large Language Models","created":"2025-10-24","cited_by_count":1,"area":"lr"},{"id":"2511.02854","title":"SELF-REDRAFT: Eliciting Intrinsic Exploration-Exploitation Balance in Test-Time Scaling for Code Generation","created":"2025-10-31","cited_by_count":1,"area":"lr"},{"id":"2511.22242","title":"Rethinking Test Time Scaling for Flow-Matching Generative Models","created":"2025-11-27","cited_by_count":1,"area":"lr"},{"id":"2602.07670","title":"Surprisal-Guided Selection: Compute-Optimal Test-Time Strategies for Execution-Grounded Code Generation","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2603.11082","title":"Quality-Driven Agentic Reasoning for LLM-Assisted Software Design: Questions-of-Thoughts (QoT) as a Time-Series Self-QA Chain","created":"2026-03-10","cited_by_count":1,"area":"lr"},{"id":"2604.15618","title":"Majority Voting for Code Generation","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.17288","title":"Clover: A Neural-Symbolic Agentic Harness with Stochastic Tree-of-Thoughts for Verified RTL Repair","created":"2026-04-19","cited_by_count":1,"area":"lr"},{"id":"2606.03852","title":"FLARE: Fine-Grained Diagnostic Feedback for LLM Code Refinement","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2606.27268","title":"E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation","created":"2026-06-25","cited_by_count":1,"area":"lr"},{"id":"2608.18027","title":"Chain-of-Experience for Continual LLM Improvement","created":"2026-08-18","cited_by_count":1,"area":null},{"id":"2608.18931","title":"Test-Time Scaling in the Wild: Why Exploitation, Not Exploration, Is the Bottleneck","created":"2026-08-19","cited_by_count":1,"area":"lr"},{"id":"2609.35947","title":"FluxLite: Inference-Time Proposal Control for Discrete Diffusion Models","created":"2026-09-28","cited_by_count":1,"area":"diffusion"},{"id":"2504.19144","title":"ChiseLLM: Unleashing the Power of Reasoning LLMs for Chisel Agile Hardware Development","created":"2025-04-27","cited_by_count":0,"area":"lr"},{"id":"2509.03310","title":"app.build: A Production Framework for Scaling Agentic Prompt-to-App Generation with Environment Scaffolding","created":"2025-09-03","cited_by_count":0,"area":"agents"},{"id":"2604.21598","title":"You Don't Need Public Tests to Generate Correct Code","created":"2026-04-23","cited_by_count":0,"area":null},{"id":"2605.09100","title":"GRC: Unifying Reasoning-Driven Generation, Retrieval and Compression","created":"2026-05-09","cited_by_count":0,"area":"lr"},{"id":"2605.11299","title":"Primal Generation, Dual Judgment: Self-Training from Test-Time Scaling","created":"2026-05-11","cited_by_count":0,"area":"lr"},{"id":"2605.22478","title":"DeliCIR: Memory-Guided Test-Time Deliberation via Multi-Agent Collaboration for Composed Image Retrieval","created":"2026-05-21","cited_by_count":0,"area":null},{"id":"2608.23632","title":"Function-Level Execution Feedback for Code Preference Optimization","created":"2026-08-23","cited_by_count":0,"area":null},{"id":"2608.28660","title":"Test-Time Scaling for Scientific Equation Discovery","created":"2026-08-21","cited_by_count":0,"area":"lr"},{"id":"2608.29322","title":"Test-Time Scaling for Video Diffusion Models via Diagnosis-Guided Candidate Recycling","created":"2026-08-29","cited_by_count":0,"area":"lr"},{"id":"2609.02849","title":"Post-Training Language Models for Gold-Medal Performance in Coding Competitions","created":"2026-09-02","cited_by_count":0,"area":"lr"},{"id":"2609.09135","title":"Entropy-Regularized Rank-Masked Policy Optimization for Test-Time Reinforcement Learning in Code Generation","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.12012","title":"Test-Driven Approaches to Software Engineering with Large Language Models: A Survey of Phases, Tasks, and Agent Skills","created":"2026-09-10","cited_by_count":0,"area":"agents"},{"id":"2609.12489","title":"Confidence-Gated Transductive Test Generation for Code Reranking","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.21208","title":"Information-Gain Rewards over Diversity-Pruned Tests: GT-Anchored Verifier Co-Training for Reliable Code Generation","created":"2026-09-18","cited_by_count":0,"area":null},{"id":"2609.26779","title":"CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents","created":"2026-09-22","cited_by_count":0,"area":"agents"},{"id":"2609.33192","title":"AG-CoT: Verified Algorithmic Traces for LLM Program Synthesis on Clifford Circuits","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33987","title":"Opera: A Verbal Critic Framework for Long-horizon Coding Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.34717","title":"ReMCTS: Reflection-Enhanced Monte Carlo Tree Search for Code Generation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.37304","title":"MetaCtrl: Your Large Language Models Can Reason Better and More Concisely with a Metacognitive Controller","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.00972","title":"VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.05170","title":"Verification Trap: Understanding Test-Time Selection Failures under False Premises in Code Generation","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.15372","title":"Fewer Bits, More Tries: Recovering Capability Under Memory Constraints","created":"2026-10-11","cited_by_count":0,"area":null}],"next_cursor":null}