paper-with-me

홈 › Papers

Auto-Configuring Scientific Simulators with Lightweight Coding-Agent Adapters

2026-06-08 · Matthew Ho, Brian Liu, Jixuan Chen, Audrey Wang, Lianhui Qin arxiv

Configuring an advanced scientific simulator, translating a modeling goal into a valid, runnable input deck, is a persistent bottleneck that costs domain scientists hours to days. Input decks are executable interfaces: simulator-specific vocabulary, cross-file references, schema constraints, and validation rules must align before a simulation can run. We show that this bottleneck can be substantially reduced with a lightweight adapter around an off-the-shelf coding agent, rather than a bespoke simulator agent. Coding agents already navigate files, edit code, run commands, and repair outputs; what they lack is the simulator's executable contract, and rebuilding the agent loop risks discarding harness-calibrated tool-use and self-correction behavior. We introduce SIGA, a coding-agent adapter that supplies this contract through retrieval, procedural memory, agent-callable validation, and validation-gated termination while leaving the model and loop frozen. Because this contract is small and external, SIGA also supports adapter self-evolution: prior trajectories can rewrite the adapter contents without modifying the underlying agent. On GEOS, a multiphysics subsurface simulator, SIGA's main gain is reliability: on harder held-out tasks it improves TreeSim from 0.720 to 0.789 and reduces across-run standard deviation by about 16x by preventing empty or invalid decks. In a human calibration, SIGA reaches in about five minutes the deck quality a domain expert reached in about three hours. Transfers to OpenFOAM and LAMMPS show the recipe is portable but interface-dependent: completion gates help when structural completeness is the bottleneck, while memory and retrieval help when value correctness is.

📄 PDF Abstract BibTeX arXiv:2606.09774

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

ADoCS: Automatic Designer of Conference Schedules

2017-04-01 · EACL 2017 4 · Diego Fern Vallejo Huanga, o, Paulina Adriana Morillo Alc{\'\i}var, C{\`e}sar Ferri Ram{\'\i}rez

Distributing papers into sessions in scientific conferences is a task consisting in grouping papers with common topics and considering the size restrictions imposed by the conference schedule. This problem can be seen as…

ArticlesClusteringInformation Retrieval

IR-SIM: A Lightweight Skill-Native Simulator for Navigation, Learning, and Benchmarking

2026-06-07 · Ruihua Han, Shuai Wang, Chengyang Li, Rui Gao 외 arxiv

Simulation plays a key role in automated robotics research supported by large language models (LLMs). However, existing simulators often require custom code or complex interfaces, creating a barrier to rapid prototyping …

Collision Avoidance

ResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research

2026-05-28 · Wanghan Xu, Shuo Li, Tianlin Ye, Qinglong Cao 외 arxiv

AI coding agents are increasingly used for scientific work, but their end-to-end autonomous research capability remains difficult to verify. We present ResearchClawBench, a benchmark for evaluating autonomous scientific …

Simulate, Reason, Decide: Scientific Reasoning with LLMs for Simulation-Driven Decision Making

2026-06-03 · Yuhan Yang, Ruipu Li, Alexander Rodríguez arxiv

Scientific simulators are increasingly being integrated into LLM-driven systems for high-stakes simulation-driven decision-making. However, existing frameworks primarily use LLMs to generate, calibrate, or execute simula…

Decision Making

Mixed neural posterior estimation for simulators with discrete and continuous parameters

2026-05-13 · Jan Boelts, Cornelius Schröder, Jonas Beck, Jakob H. Macke 외 arxiv

Neural Posterior Estimation (NPE) enables rapid parameter inference for complex simulators with intractable likelihoods. NPE trains an inference network to estimate a probability density over parameters given data, typic…