{"total":76,"rows":[{"id":"2602.21193","title":"On Data Engineering for Scaling LLM Terminal Capabilities","created":"2026-02-24","cited_by_count":43,"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":"2509.24663","title":"InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation","created":"2025-09-29","cited_by_count":32,"area":null},{"id":"2510.19898","title":"BugPilot: Complex Bug Generation for Efficient Learning of SWE Skills","created":"2025-10-22","cited_by_count":30,"area":null},{"id":"2510.02453","title":"How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models","created":"2025-10-02","cited_by_count":24,"area":null},{"id":"2606.07682","title":"SWE-Marathon: Can Agents Autonomously Complete Ultra-Long-Horizon Software Work?","created":"2026-06-05","cited_by_count":23,"area":null},{"id":"2604.25727","title":"Toward Scalable Terminal Task Synthesis via Skill Graphs","created":"2026-04-28","cited_by_count":22,"area":null},{"id":"2602.02361","title":"SWE-Universe: Scale Real-World Verifiable Environments to Millions","created":"2026-02-02","cited_by_count":19,"area":null},{"id":"2509.22638","title":"Language Models Can Learn from Verbal Feedback Without Scalar Rewards","created":"2025-09-26","cited_by_count":18,"area":null},{"id":"2505.16975","title":"SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development","created":"2025-05-22","cited_by_count":16,"area":null},{"id":"2607.13988","title":"TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents","created":"2026-07-15","cited_by_count":16,"area":null},{"id":"2602.21492","title":"GradAlign: Gradient-Aligned Data Selection for LLM Reinforcement Learning","created":"2026-02-25","cited_by_count":12,"area":null},{"id":"2506.08140","title":"AutoSDT: Scaling Data-Driven Discovery Tasks Toward Open Co-Scientists","created":"2025-06-09","cited_by_count":11,"area":null},{"id":"2507.11059","title":"SWE-MERA: A Dynamic Benchmark for Agenticly Evaluating Large Language Models on Software Engineering Tasks","created":"2025-07-15","cited_by_count":9,"area":null},{"id":"2606.03461","title":"What Makes Interaction Trajectories Effective for Training Terminal Agents?","created":"2026-06-02","cited_by_count":9,"area":null},{"id":"2603.15611","title":"Code-A1: Adversarial Evolving of Code LLM and Test LLM via Reinforcement Learning","created":"2026-03-16","cited_by_count":8,"area":null},{"id":"2605.29559","title":"LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents","created":"2026-05-28","cited_by_count":8,"area":null},{"id":"2606.12344","title":"Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks","created":"2026-06-10","cited_by_count":8,"area":null},{"id":"2609.04148","title":"Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments","created":"2026-09-03","cited_by_count":8,"area":null},{"id":"2506.10954","title":"SWE-Factory: Your Automated Factory for Issue Resolution Training Data and Evaluation Benchmarks","created":"2025-06-12","cited_by_count":7,"area":null},{"id":"2608.13951","title":"HELIX: Model-Harness Co-evolution for Recursive Self-Improvement","created":"2026-08-14","cited_by_count":7,"area":null},{"id":"2604.11716","title":"SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context","created":"2026-04-13","cited_by_count":6,"area":null},{"id":"2512.20482","title":"SweRank+: Multilingual, Multi-Turn Code Ranking for Software Issue Localization","created":"2025-12-23","cited_by_count":5,"area":null},{"id":"2510.03178","title":"When Names Disappear: Revealing What LLMs Actually Understand About Code","created":"2025-10-03","cited_by_count":4,"area":null},{"id":"2510.14826","title":"To Infinity and Beyond: Tool-Use Unlocks Length Generalization in State Space Models","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2601.13713","title":"SWE-Tester: Training Open-Source LLMs for Issue Reproduction in Real-World Repositories","created":"2026-01-20","cited_by_count":4,"area":null},{"id":"2601.17789","title":"Neuro-Symbolic Verification on Instruction Following of LLMs","created":"2026-01-25","cited_by_count":4,"area":null},{"id":"2601.22859","title":"MEnvAgent: Scalable Polyglot Environment Construction for Verifiable Software Engineering","created":"2026-01-30","cited_by_count":4,"area":null},{"id":"2605.22175","title":"SWE-Mutation: Can LLMs Generate Reliable Test Suites in Software Engineering?","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2608.26530","title":"PILOT in the Loop: Live Self-Improvement for Long-Horizon Agents","created":"2026-08-27","cited_by_count":4,"area":null},{"id":"2608.27449","title":"SWE-Prime: Fewer Trajectories, Better Performance","created":"2026-08-27","cited_by_count":4,"area":null},{"id":"2609.19134","title":"ScienceIDE: Turning World's Scientific Codebase into Agent Learnable Environments","created":"2026-09-16","cited_by_count":4,"area":null},{"id":"2603.06739","title":"ResearchEnvBench: Benchmarking Agents on Environment Synthesis for Research Code Execution","created":"2026-03-06","cited_by_count":3,"area":null},{"id":"2605.14445","title":"FrontierSmith: Synthesizing Open-Ended Coding Problems at Scale","created":"2026-05-14","cited_by_count":3,"area":null},{"id":"2605.26177","title":"RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations","created":"2026-05-25","cited_by_count":3,"area":null},{"id":"2608.03571","title":"Beyond Simply Environment Scaling: Designing Effective Environment Distributions for Multimodal Agent Learning","created":"2026-08-04","cited_by_count":3,"area":null},{"id":"2509.24148","title":"TENET: One Step Toward Test-Driven Development for Repository-Level Code Generation","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2601.19362","title":"Revisiting Parameter Server in LLM Post-Training","created":"2026-01-27","cited_by_count":2,"area":null},{"id":"2604.17338","title":"Precise Debugging Benchmark: Is Your Model Debugging or Regenerating?","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2605.15222","title":"PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2607.07435","title":"RLVP: Penalize the Path, Reward the Outcome","created":"2026-07-08","cited_by_count":2,"area":null},{"id":"2607.15205","title":"MM-IssueLoc: A Controlled Benchmark for Evaluating Visual Evidence in Multimodal Repository-Level Issue Localization","created":"2026-07-16","cited_by_count":2,"area":null},{"id":"2608.08570","title":"FailForge: Distilling Procedural Competence from Persistent Failures into Code Agents","created":"2026-08-09","cited_by_count":2,"area":null},{"id":"2608.13566","title":"Don't Claim Benchmark-Oriented Optimization Improves General Coding Capability -- Diverse Evaluation Is Required","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2602.07457","title":"Pull Requests as a Training Signal for Repo-Level Code Editing","created":"2026-02-07","cited_by_count":1,"area":null},{"id":"2603.11356","title":"Resolving Java Code Repository Issues with iSWE Agent","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2604.16021","title":"Neurosymbolic Repo-level Code Localization","created":"2026-04-17","cited_by_count":1,"area":null},{"id":"2604.27977","title":"D3-Gym: Constructing Real-World Verifiable Environments for Data-Driven Discovery","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2607.28587","title":"PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks","created":"2026-07-30","cited_by_count":1,"area":null},{"id":"2610.04184","title":"EvalResearchBench: Can AI Agents Design Their Own Evaluations?","created":"2026-10-03","cited_by_count":1,"area":null},{"id":"2610.10426","title":"CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution","created":"2026-10-07","cited_by_count":1,"area":null},{"id":"2601.18119","title":"Beyond Text-to-SQL: Can LLMs Really Debug Enterprise ETL SQL?","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2601.18241","title":"TAM-Eval: Evaluating LLMs for Automated Unit Test Maintenance","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2604.12108","title":"LLM-Based Automated Diagnosis Of Integration Test Failures At Google","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2605.26100","title":"Beyond Summaries: Structure-Aware Labeling of Code Changes with Large Language Models","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2605.29115","title":"unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2606.07527","title":"Post-training is (Massive) Supervised Learning","created":"2026-04-20","cited_by_count":0,"area":null},{"id":"2606.11416","title":"MPC-Patch-Bench: Security-Aware LLM Code Patch for Multi-Party Computation","created":"2026-06-09","cited_by_count":0,"area":null},{"id":"2606.14357","title":"No Accidental Software Agent First Canonical Code for Human Code Entropy Reduction and 30 to 500 times Lower Frontier Model Requirements","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2607.00700","title":"LLVM-Bench: Benchmarking and Advancing Large Language Models for LLVM Compiler Issue Resolution","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.05473","title":"Binocular Gaze Estimation with Single Camera and Single Light Source","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.05156","title":"Scaffold-Mediated Post-Training: Co-Evolving Model Parameters and Procedural Scaffold Graphs","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2608.18280","title":"What Makes Software Issue Resolution Tasks Difficult for Agents?","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.08418","title":"Feyospace-v1: How the Cyber Mercury Seven Trained Frontier Cyber Models","created":"2026-09-08","cited_by_count":0,"area":null},{"id":"2609.12475","title":"Zipbench: Low-Cost Framework for Compressing Comprehensive Benchmarks of Large Language Models","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.32662","title":"AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.32835","title":"FinancialAuditBench: Benchmark Construction under Differential Privacy Using Real-World Priors","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33772","title":"Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.40097","title":"AutoDataBench: A Data-centric Testbed for Accelerating Auto Research","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.40330","title":"Turbo Harness: Instance-Adaptive Harness Optimization","created":"2026-09-30","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},{"id":"2610.15345","title":"CodeWalk: Generating Coding Benchmarks by Walking a Problem Graph","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.18484","title":"ReTerm: Recovery Training for Self-Improving Terminal Agents","created":"2026-10-13","cited_by_count":0,"area":null},{"id":"2610.19801","title":"Delta Tokenizer: Reference-Identical Tokenization of Session Deltas and Segment-Parallelism for Long Prompts on Multicore CPUs","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.20038","title":"SWE-Nexus: Automated Composition of Software Engineering Tasks from Test Execution","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.20256","title":"Long-Horizon RL Needs Muon","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}