2026-10-14T03:26:27Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33991367 2026-09-25T02:03:35Z category_7 category_272 category_39 category_45 category_734 portal_63 item_type_2 month_year_09_2026

Auditable Automation of Activated Sludge Modeling for Wastewater Treatment Diagnosis Using LLM-Agents Yu-Qi Wang (1538104) Hao-Lin Yang (21375532) Jia-Ji Chen (19740668) Wen-Zhe Wang (10105287) Yun-Peng Song (18810717) Ai-Jie Wang (1957156) Hong-Cheng Wang (48817) Medicine Environmental Sciences not elsewhere classified Ecology Sociology Biological Sciences not elsewhere classified still depends heavily scale wwtp provided optional human review need mechanistic models level performance within average accuracy scores ablation experiments evaluated source langgraph code changing operating conditions activated sludge modeling constrained asm configuration workflow converts wastewater agent skill implementations 41 biochemical reactions predefined asm library environmental modeling claude code asm instantiated tested workflow structured configurations single agent reproducible development reflection modules provide open process descriptions phosphorus transformations narrow range model agent explain carbon expert choices efficiency trade data conditions boundary specification auditable large auditable automation agent workflows Wastewater treatment plants (WWTPs) need mechanistic models that explain carbon, nitrogen, and phosphorus transformations under changing operating conditions. Building activated sludge models (ASMs) still depends heavily on expert choices about boundaries, components, and reactions. We developed AutoWWTP-ASM, an auditable large-language-model agent (LLM-Agent) workflow for library-constrained ASM configuration, execution, and calibration. The workflow converts wastewater-process descriptions into structured configurations and combines a predefined ASM library with boundary specification and optional human review. In a coupled carbon−nitrogen−phosphorus task, AutoWWTP-ASM instantiated a model containing 21 state components and 41 biochemical reactions. Across 37 evaluation tasks, the average accuracy scores of ten LLM backbones ranged from 0.596 to 0.627, indicating a narrow range of backbone-level performance within the tested workflow. Ablation experiments evaluated the knowledge, planning, and reflection modules. Comparisons with a single agent, an 8B LLM, and human modelers assessed deployment and efficiency trade-offs. Additional evaluations using six IWA BSM1 scenarios and data from a full-scale WWTP provided further evidence of applicability under standardized and real-data conditions. We provide open-source LangGraph code, together with Codex, Claude Code, and Agent Skill implementations, to support the reproducible development of auditable LLM-Agent workflows for environmental modeling. 2026-09-24T00:00:00Z Dataset Media 10.1021/acs.est.6c09278.s001 https://figshare.com/articles/media/Auditable_Automation_of_Activated_Sludge_Modeling_for_Wastewater_Treatment_Diagnosis_Using_LLM-Agents/33991367 CC BY-NC 4.0