The study evaluates local open‑weight large language model agents for data‑engineering tasks, using a benchmark of fifteen mobility‑workflow tasks that cover discovery, processing, enrichment, and reporting. Ten local model configurations were tested in one‑shot and closed‑loop conditions, producing 1,500 scored attempts on a consumer‑grade GPU. Results show that models larger than two billion parameters achieve up to 85.3% artifact‑level success, with closed‑loop workspaces boosting pass rates by 26.7–52.0 percentage points, and a quantized 9‑billion‑parameter model reaching 69.3% success with a 6.5 GB memory footprint.
arXiv:2607. 14896v1 Announce Type: cross Abstract: Addressing a structural-engineering request requires more than a single answer; it requires a chain of interdependent artifacts: interpreted requirements, a computable model, validation records, solver outputs, code-check records, and a final report.
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:2607. 16617v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to automate data-processing workflows, yet coding agents typically produce scripts that are not automatically materialized as persistent, editable platform artifacts.
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:2608. 10366v1 Announce Type: new Abstract: Real-world data science involves long-horizon workflows that span data wrangling, exploration, modeling, visualization, and validation, and require coordinated use of tools such as notebooks, IDEs, terminals, browsers, and databases within real operating environments.
arXiv:2607. 01647v1 Announce Type: cross Abstract: Data science aims to derive actionable insights from heterogeneous raw data, unlocking the value of the massive amounts of data generated in modern society.
EngiAI introduces a capability-based evaluation framework for tool-connected engineering agents, assessing workflow execution, retrieval-assisted parameter selection, HPC orchestration, and training-code authoring using execution traces and engineering artifacts. The framework was applied to four LLM backends on EngiBench Beams2D and Photonics2D, revealing that proprietary models outperform open-source ones in workflow completion and HPC orchestration, while indexed retrieval improves parameter selection. The study demonstrates that evaluating distinct skills separately provides clearer insight into failure mechanisms than end-to-end success rates alone.
arXiv:2606. 12674v1 Announce Type: new Abstract: Compact language models (LMs) reduce cost, latency, and deployment risk for tool agents.
arXiv:2608. 10039v1 Announce Type: new Abstract: Agentic workflows have become an important abstraction for building reliable LLM-based automation systems by organizing large language models (LLMs), tools, and control logic into explicit execution structures.
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:2607. 03953v1 Announce Type: cross Abstract: This study independently replicates and extends the Natural Language Tools (NLT) framework of Johnson et al.
E2E-SWE is a benchmark that tests large language models’ ability to create complete, functional software repositories from scratch. It includes 186 tasks across 11 programming languages, each requiring an agent to build an installable project based solely on a natural‑language specification and an empty workspace, while passing a hidden test suite. The benchmark was crafted by software engineers and LLMs, then refined through iterative verification by autonomous agents to ensure clarity and solvability.