{"total":18,"rows":[{"id":"2606.17861","title":"GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?","created":"2026-06-16","cited_by_count":22,"area":"agents"},{"id":"2607.03525","title":"GameEngineBench: Evaluating Coding Agents on Real C++ Runtime Environments","created":"2026-07-03","cited_by_count":9,"area":"agents"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2608.21833","title":"GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?","created":"2026-08-22","cited_by_count":8,"area":"agents"},{"id":"2609.21562","title":"GameLogicBench: Evaluating Coding Agents on Runtime Game Logic with Tick-Level State Assertions","created":"2026-09-18","cited_by_count":2,"area":"agents"},{"id":"2609.29718","title":"PPTBench: Can Coding Agents Reconstruct the Visual World through Structured, Editable Slides","created":"2026-08-31","cited_by_count":1,"area":"agents"},{"id":"2609.39045","title":"RSIGame: Autonomous Agentic Game Development with Recursive Self-improvement","created":"2026-09-30","cited_by_count":1,"area":"agents"},{"id":"2608.29889","title":"VibeJam: A User Study Platform for Web Development with Agents","created":"2026-08-30","cited_by_count":0,"area":"agents"},{"id":"2609.18996","title":"Compiled Agency: Frontier General-Purpose Coding Agents Build Winning Game Players from Bare Interaction - from Flappy Bird to StarCraft II and Civilization","created":"2026-07-17","cited_by_count":0,"area":"agents"},{"id":"2609.23142","title":"CraftBench-UE: Deterministic Evaluation for Coding Agents in Unreal Engine","created":"2026-09-19","cited_by_count":0,"area":"agents"},{"id":"2609.32600","title":"CUA-SWE: When Computer-Use Agents Meet Visual Software Engineering","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.33678","title":"SWE-Game: Can Coding Agents Build the Games We Want?","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.39564","title":"A2Z GameSpec-Bench: How Faithfully Can Coding Agents Generate Games from Game Design Specifications?","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.02563","title":"OpenGameEval: Benchmarking Agentic Programming and Exploration in a Stateful Game Engine","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.06910","title":"GAMEGO: Training Game-Dev Agents with Synthetic Trajectories Anchored in Real-World Assets","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.08621","title":"Recursive Game Creator: An Agentic Product-Level Experience-Oriented Game Harness","created":"2026-10-06","cited_by_count":0,"area":"agents"},{"id":"2610.15708","title":"SpecForge: Recursive Self-Improvement for Coding Agents via Behavioral Specifications","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.20584","title":"Player-1: Learning to Play from Synthetic Experience","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}