ViBench 2.0 is a new benchmark for long‑horizon software building, featuring 17 full‑stack web products that evolve through 241 feature requests. The benchmark evaluates models only when the entire product is finished, using 544 test plans per product to ensure a strict grading protocol. Initial results show a reliability gap: top models pass most test plans but rarely deliver fully working products, though recent releases have improved performance significantly.
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...
AgentSWE is a new benchmark for agent software engineering that evaluates coding agents across three lifecycle stages: creating an agent from a natural‑language requirement, editing existing agent codebases, and optimizing toward a measurable target. The benchmark consists of 25 commission‑style tasks, where builders iterate on a few illustrative cases and are then tested on held‑out cases that cover the full requirement, with hard pass/fail gates or objective‑based grading. Experiments show that current coding agents fail to meet the requirements, revealing common failure modes such as overfitting, incomplete runtimes, and unsupported completion claims.
arXiv:2510. 09801v3 Announce Type: replace Abstract: While benchmarks measure the accuracy of LLM-powered agents, they mostly assume full automation, failing to represent the collaborative nature of real-world use cases.
arXiv:2608.22510v1 Announce Type: new Abstract: Agent benchmarks often evaluate only final answers even when agents run on stateful runtimes. We argue this under-specifies what is being evaluated: th...
arXiv:2606. 19613v1 Announce Type: cross Abstract: We introduce StaminaBench, a benchmark that measures the stamina of coding agents: how many consecutive interaction turns (change requests) they can handle before failing.
arXiv:2609.23570v1 Announce Type: cross Abstract: Coding agents operate on real repository coding tasks, and persistent memory systems promise to reuse experience across tasks. Yet existing evaluatio...
arXiv:2608.28795v1 Announce Type: cross Abstract: Modern artificial-intelligence coding agents can be equipped with tools for checking their own work e.g. a linter, a boot probe, a shell, a screensho...
arXiv:2609.06059v1 Announce Type: new Abstract: As large language models evolve from question-answering systems into general-purpose agents, evaluation must move beyond static answer correctness to a...
arXiv:2609.38269v1 Announce Type: cross Abstract: Coding agents are increasingly asked to build software rather than patch it, yet benchmarks for from-scratch repository construction are mostly limit...
arXiv:2607. 02436v1 Announce Type: cross Abstract: Agentic coding assistants are increasingly given extra capabilities, such as browser based testing tools and design oriented system prompts, on the assumption that more capability yields better software.
UniACE is a unified framework that standardizes the evaluation of large language model (LLM) agents by representing each benchmark as an instruction–tool–environment triplet and running models through a shared, task‑agnostic harness in isolated runtimes. It preserves native success criteria, offers an offline mode for dynamic‑resource tasks, and standardizes efficiency metrics, execution records, and failure attribution. Applying UniACE to 7 benchmarks across 24 domains and 15 models revealed significant score shifts, ranking reversals, and sensitivity to evidence representation, highlighting the impact of evaluation configuration on reported agent performance.
arXiv:2605. 27898v2 Announce Type: replace Abstract: As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential.