cs.AINov 14, 2026

Does a completed simulation run mean a usable urban wind result for AI agents?

Authors: Zhongke Qu, Yunwei Zhang, Junwei Su, Yabin Zhang, Chengwei Li, Qingxiang Shui, Hailong Qu, Zhaolin Gu

Organizations: School of Human Settlements and Civil Engineering, Xi’an Jiaotong University, Xi’an 710049, China · Shaanxi Institute of Meteorological Science,Xi'an, China · Shaanxi Provincial Atmospheric Observation Technical Support Center, Xi'an,China · Xihua University, School of Energy and Power Engineering · 

Abstract

AI agents based on large language models (LLMs) can now configure and run computational fluid dynamics (CFD) solvers, but a completed run does not ensure that delivered metrics can be recomputed from raw outputs. This gap was examined for urban wind simulation, where multi-case comparisons must hold non-target conditions fixed and reported values must be traceable to raw samples. UrbanWind-AgentBench, comprising 200 tasks and 367 cases in 10 engineering task families, was constructed. Public task contracts specify variable factors, fixed conditions, numerical thresholds and deliverable requirements, and two-layer scoring separates a structural score for deliverables, run provenance and raw evidence from a numerical score obtained by independent recomputation against references. WindPilot was then proposed as an execution framework that incorporates contract parsing, execution provenance, deterministic verification and bounded acceptance review into the LLM execution loop. On 30 OpenFOAM tasks with independent references, at least the structural maximum of 60 points was reached by a base agent on 28 tasks, but numerical credit was obtained on only 6. With the same model name and budget, WindPilot increased the number of tasks with numerical credit to 17, full-score tasks from 0 to 3 and the mean task score from 62.5 to 72.5. Mean action steps fell from 130.4 to 104.9, and mean token consumption decreased by 12.9%. The mean gain for atmospheric boundary layer (ABL) tasks was 18.5 points. A completed simulation run is therefore not sufficient for a usable urban wind result; usability depends on checks that tie reported metrics to raw evidence during execution.

Explore similar work

Jun 26, 2026

GenWorld: Empirically Grounded Urban Simulation Infrastructure for Scalable LLM-Agent Studies

LLM-agent simulation faces a joint grounding and scaling problem: agents should act in environments that reflect real urban constraints, yet direct online LLM calls for city-scale populations are computationally prohibitive. We present GenWorld, an empirically grounded urban simulation infrastructure that combines a building-level synthetic city, a structured agent-environment interface, and offline compilation of LLM-derived decision signals into lookup policies for scalable rollout. In a reference instantiation for Higashihiroshima, Japan, GenWorld grounds 196,608 synthetic residents in census and geospatial data, validates demographic consistency against census tabulations, and uses YJMob100K mobile-phone data as a commuting-distance diagnostic. We demonstrate the infrastructure through three reproducible cases: a full-city weekday rollout, a weekday-weekend behavioral contrast, and a warning-response perturbation with auditable replanning traces. These cases support GenWorld as a reproducible platform for grounded and scalable LLM-agent studies, while calibrated forecasting for traffic, evacuation, or policy outcomes remains future work.
May 11, 2026

WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation

Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks still rely on synthetic sandboxes, short-horizon tasks, mock-service APIs, and final-answer checks, leaving open whether agents can complete realistic long-horizon work in the runtimes where they are deployed. This work presents WildClawBench, a native-runtime benchmark of 60 human-authored, bilingual, multimodal tasks spanning six thematic categories. Each task averages roughly 8 minutes of wall-clock time and over 20 tool calls, and runs inside a reproducible Docker container hosting an actual CLI agent harness (OpenClaw, Claude Code, Codex, or Hermes Agent) with access to real tools rather than mock services. Grading is hybrid, combining deterministic rule-based checks, environment-state auditing of side effects, and an LLM/VLM judge for semantic verification. Across 19 frontier models, the best, Claude Opus 4.7, reaches only 62.2% overall under OpenClaw, while every other model stays below 60%, and switching harness alone shifts a single model by up to 18 points. These results show that long-horizon, native-runtime agent evaluation remains a far-from-resolved task for current frontier models. We release the tasks, code, and containerized tooling to support reproducible evaluation.
Sep 27, 2026

Identical Runs, Different Results: Benchmarking AI Coding Agents on Open-Weight Models

Repeated runs of the same coding agent are known to give different benchmark scores. We ask what that variation means for a team running an agent on its own task, by intensive replication on one machine-learning task: an agent improves the training code of an XGBoost classifier for airline delays, and a holdout it never sees scores the result. Across 584 runs, we compare six agents on six open-weight model endpoints, run six agent-model pairings 52 times each under fixed settings, and repeat three of them on a larger model from the same family. Identical runs of one pairing varied more than the pairings differed from one another, so comparisons of a few runs ranked them unreliably; resolving the agent differences we observed would take tens to more than a hundred runs of each. Runs on the larger model scored clearly higher, but by less than one run-to-run standard deviation, and the gap was more than twice as large with one agent as with the others. Fewer than one run in twenty broke the task's data rules, but those runs held the highest scores. Rejecting those runs first and keeping the best compliant result among a few attempts reliably improved the delivered model, even though a few runs could not rank the agents. On flights from a later year, the delivered models kept only a third of their gain over the starting code. At list prices, cost differed more than twentyfold between two agents on the same model, mostly through the prompt cache. Agents and models should be evaluated as pairings, over repeated attempts, with compliance reported beside quality. Data, code and every delivered program: https://github.com/earino/identical-runs-different-results