arXiv:2606. 29957v1 Announce Type: cross Abstract: Most coding-agent benchmarks are static: an agent receives a complete task description up front and is judged only by its final code.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
ProgramDistill is a benchmark that evaluates coding agents by having them infer and implement features discovered through interaction with fully functional reference web applications. The benchmark is built by factorizing applications into features of varying granularity, each linked to replayable behaviors that can be executed via a gold patch. Using a mine‑craft‑patch pipeline, the authors discovered 1,975 replay‑verified behaviors across 26 applications and automatically constructed 4,063 tasks, enabling evaluation of nine frontier coding agents, including GPT‑6 Astra and Claude Opus 5, on both full‑application and partial‑application reconstruction tasks.
arXiv:2606. 30573v1 Announce Type: new Abstract: We introduce SWE-Interact, a new testbed for evaluating coding agents on multi-turn, interactive, user-driven software engineering tasks.
arXiv:2606. 07682v1 Announce Type: cross Abstract: AI agents are increasingly expected to complete long-horizon workflows that require sustained progress over hours, millions of tokens, and complex environments.
arXiv:2609.21423v1 Announce Type: new Abstract: Online agent deployments produce abundant execution traces, while task-specific verification and expert annotation are costly to scale. We study how to...
arXiv:2609.22000v1 Announce Type: new Abstract: Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Re...
arXiv:2605. 25160v2 Announce Type: replace Abstract: GUI agents powered by large language models are advancing rapidly, creating urgent needs for evaluation and training based on realistic environments.