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: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: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.
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:2610.27954v1 Announce Type: new Abstract: Recent advances in large (vision) language models have enabled computer-use agents that automate digital workflows via fine-grained keyboard and mouse...
SWE-Shift is a new benchmark that tests coding agents in environments where tasks and workspaces can change mid-execution. It presents 120 scenarios across 12 change families, each evaluated at nine intervention points, comparing a Clean continuation (no change) with a Shifted continuation (task-relevant update). The benchmark shows that all evaluated agents perform better on Clean than on Shifted, with significant drops in success rates and zero paired success for certain change types.
arXiv:2607. 28591v1 Announce Type: cross Abstract: Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation.
WebAnything is a fully automated framework that reconstructs source‑grounded, reusable web environments from real URLs without per‑site manual engineering. It uses an Explorer‑Builder to collect browser‑observable structures and an independent verifier to ensure fidelity, producing 244 website artifacts across 14 domains and 53 categories with 12,984 executed tasks. Compared to human‑assisted WebHarbor, WebAnything scores higher on three fidelity metrics and, when fine‑tuned with Qwen3.5‑9B, improves success rates across multiple benchmarks.
arXiv:2610.16402v1 Announce Type: new Abstract: Web application development often proceeds through successive requests that extend an existing implementation. Yet web-generation benchmarks primarily...
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:2610.09079v1 Announce Type: cross Abstract: Large language models equipped with development environments have moved code generation toward repository-scale construction, yet building complete r...
ProgramGym introduces a scalable framework for training long-horizon program reproduction agents, comprising Program-Env and Program-Agent components. Program-Env builds verifiable training environments from repositories via a feedback loop that repairs sandbox builds and improves black-box tests, yielding 1,648 environments across C, C++, Go, and Rust. Program-Agent employs a role-isolated workflow of analysis, implementation, and review with revision management, boosting performance on ProgramBench and raising Qwen3.8-27B’s accuracy from 34.87% to 42.84% and surpassing flagship models with fine-tuning.
SWEPatchTest is a benchmark that evaluates software tests by measuring their ability to reproduce issues, accept correct patches, and reject incorrect ones across 619 tasks and 82,579 candidate patches. It introduces the Joint Validation Rate metric, revealing that even the best configurations only achieve 9.21% success when all three criteria are met. Using these validation scores to select demonstrations for supervised fine‑tuning can roughly triple the Joint Validation Rate and enhance downstream repair performance on multiple SWE‑bench datasets.