{"total":60,"rows":[{"id":"2604.17308","title":"SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents","created":"2026-04-19","cited_by_count":25,"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":"2605.18661","title":"AI for Auto-Research: Roadmap & User Guide","created":"2026-05-18","cited_by_count":11,"area":null},{"id":"2603.01203","title":"How Well Does Agent Development Reflect Real-World Work?","created":"2026-03-01","cited_by_count":10,"area":null},{"id":"2601.05106","title":"Token-Level LLM Collaboration via FusionRoute","created":"2026-01-08","cited_by_count":9,"area":null},{"id":"2603.04601","title":"Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development","created":"2026-03-04","cited_by_count":9,"area":null},{"id":"2605.26548","title":"SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?","created":"2026-05-26","cited_by_count":9,"area":null},{"id":"2601.11895","title":"DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models","created":"2026-01-17","cited_by_count":8,"area":null},{"id":"2603.13428","title":"SWE-Milestone: Evaluating AI Agents on Continuous Software Evolution","created":"2026-03-13","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":"2608.06352","title":"CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks","created":"2026-08-06","cited_by_count":8,"area":null},{"id":"2606.17930","title":"How Inference Compute Shapes Frontier LLM Evaluation","created":"2026-06-16","cited_by_count":7,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2606.30182","title":"MirrorCode: AI can rebuild entire programs from behavior alone","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2606.00408","title":"Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism","created":"2026-05-29","cited_by_count":5,"area":null},{"id":"2601.20886","title":"IDE-Bench: Evaluating Large Language Models as IDE Agents on Real-World Software Engineering Tasks","created":"2026-01-28","cited_by_count":4,"area":null},{"id":"2605.02944","title":"Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation","created":"2026-05-01","cited_by_count":4,"area":null},{"id":"2608.17271","title":"ASI-Bench: At the Dawn of Artificial Superintelligence","created":"2026-08-18","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":"2604.06111","title":"AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments","created":"2026-04-07","cited_by_count":3,"area":null},{"id":"2605.07024","title":"Delulu: A Verified Multi-Lingual Benchmark for Code Hallucination Detection in Fill-in-the-Middle Tasks","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2605.21463","title":"Mem-$\\pi$: Adaptive Memory through Learning When and What to Generate","created":"2026-05-20","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":"2607.19653","title":"PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2609.17930","title":"Locating Hidden Failures Makes Long-Horizon Agents More Reliable","created":"2026-09-15","cited_by_count":3,"area":null},{"id":"2603.05026","title":"RepoLaunch: Automating Build and Management of Code Repositories across Languages and Platforms","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2603.15798","title":"CUBE: A Standard for Unifying Agent Benchmarks","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2606.17454","title":"Dissecting model behavior through agent trajectories","created":"2026-06-16","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":"2608.15242","title":"LongRCA Bench: Root-Cause Localization in Long-Horizon Agent Trajectories","created":"2026-08-15","cited_by_count":2,"area":null},{"id":"2609.06396","title":"MetaRSI / RSI2: A Meta-Recursive Self-Improving System for Recursive Self-Improving Systems Themselves","created":"2026-09-06","cited_by_count":2,"area":null},{"id":"2610.07557","title":"CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?","created":"2026-10-06","cited_by_count":2,"area":null},{"id":"2511.20613","title":"Can Vibe Coding Beat Graduate CS Students? An LLM vs. Human Coding Tournament on Market-driven Strategic Planning","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2602.16902","title":"LLM-WikiRace Benchmark: How Far Can LLMs Plan over Real-World Knowledge Graphs?","created":"2026-02-18","cited_by_count":1,"area":null},{"id":"2603.10002","title":"SpreadsheetArena: Decomposing Preference in LLM Generation of Spreadsheet Workbooks","created":"2026-02-16","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":"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":"2608.20634","title":"AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale","created":"2026-08-21","cited_by_count":1,"area":null},{"id":"2609.38345","title":"OpenCollab: A Multi-Agent Coding Framework with Programmable Collaboration and Controllable Runtime","created":"2026-09-29","cited_by_count":1,"area":null},{"id":"2604.24966","title":"Risk Reporting for Developers' Internal AI Model Use","created":"2026-04-27","cited_by_count":0,"area":null},{"id":"2606.05486","title":"Localizing Prompt Ambiguity in Large Language Models with Probe-Targeted Attribution","created":"2026-06-03","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":"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":"2607.27283","title":"Benchmarking the Residual: What Long-Horizon Evaluations Add Beyond Matched Short-Task Performance","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2608.05797","title":"Predicting Task Difficulty Without Rollouts","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.06422","title":"Sharding Prevents LLM Oversight Failures and Adversarial Exploitation","created":"2026-08-05","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":"2608.20664","title":"DreamBench-SWE: A Multi-Session Memory-Hygiene Benchmark for Software Agents","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.05779","title":"Diffs vs. Whole Files: An Empirical Comparison of Iterative Edit-Based and Direct Generation for Flutter/Dart Code Models","created":"2026-09-05","cited_by_count":0,"area":null},{"id":"2609.07784","title":"xDailyBench: Benchmarking LLMs on Professional Consultation for Real-Life Problems","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.23939","title":"XYEval: Agents say yes to bad advice","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.35236","title":"Long-Horizon Scaling: How Model Capabilities Shape the Returns to Computation","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.36675","title":"G\\\"odel Forest: Balancing Search Depth and Breadth for Data-Centric Recursive Self-Improvement","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2609.39086","title":"Trustworthy Runtime Error Healing in Real-World Repositories: A Benchmark and Guardrail","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2610.04658","title":"RETRACE: From Entangled Repair Histories to Reusable Experience for CI Repair","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.11424","title":"Why machines will still not rule the world","created":"2026-10-08","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":"2610.19843","title":"LAGO: Language Agents with Reusable Growing Options","created":"2026-10-14","cited_by_count":0,"area":null},{"id":"2610.19948","title":"When Protection Overrides Consequences: Understanding Protection Mode in Large Language Model Decision-Making","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}