Auto-Configuring Scientific Simulators with Lightweight Coding-Agent Adapters
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
ADoCS: Automatic Designer of Conference Schedules
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 RetrievalIR-SIM: A Lightweight Skill-Native Simulator for Navigation, Learning, and Benchmarking
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 AvoidanceResearchClawBench: A Benchmark for End-to-End Autonomous Scientific Research
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
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 MakingMixed neural posterior estimation for simulators with discrete and continuous parameters
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…