AutoEnergyDesign is an LLM‑driven framework that optimizes building energy system designs by iteratively proposing configuration changes based on prior simulation results and automatically reverting unsuccessful changes via a git‑based mechanism. The agent combines a reasoning model with explicit memory (procedural, semantic, episodic, reflective), a constrained action interface, and a keep/revert signal, and evaluates designs using a 25‑year Net Present Cost model across eight technologies. In a case study with measured building loads, the agent (using Claude Haiku 5.5, Sonnet 5.5, and Opus 5.5) achieved an NPC within 1% of the best baseline after far fewer simulations, outperforming random search, TPE Bayesian optimization, and a $(1+1)$ evolution strategy.
arXiv:2606. 20950v2 Announce Type: replace Abstract: Executable evaluation -- checking the consequences of an agent's actions with a program rather than grading its prose -- has become a prominent way to assess tool-using AI agents in software settings.
arXiv:2607. 18147v1 Announce Type: cross Abstract: Large language models (LLMs) and agentic AI systems have evolved from natural language tasks to using external tools to plan, retrieve, and act in technical domains.
arXiv:2611.07372v1 Announce Type: new Abstract: An LLM agent's cost and success depend on its model, its harness, and its environment. In addition to the widely studied directions of parameter tuning...
arXiv:2606. 09037v2 Announce Type: replace Abstract: This study presents a large language model (LLM)-based multi-agent framework for interior permanent magnet synchronous motor (IPMSM) design optimization that mitigates limitations of conventional workflows: expertise-dependent problem setup and data preparation, the prohibitive computational cost of finite element analysis (FEA), and the unreliability of AI surrogates in unexplored regions.
arXiv:2608.21976v1 Announce Type: new Abstract: Agentic AI has automated parts of scientific discovery, including paper generation, expert-level coding, therapeutic proposal, and autonomous experimen...
The paper presents an integrated approach that combines large language models (LLMs) with numerical solvers to accelerate redesign in engineering, specifically targeting electric vehicle battery pack cost minimization. Three LLM integration strategies—warm start, variable fixing, and ReAct—are evaluated alongside four black-box solvers, showing that the integrated method can achieve comparable design quality with 80% fewer simulator evaluations and a higher rate of near-optimal solutions. The study highlights that the optimal LLM-solver pairing depends on the nature of the redesign scenario and that larger LLMs provide greater benefits when they exert more control over the search process.
RSI-Opt introduces Recursive Self-Improvement Optimizer Agents that evolve their own training policies by accumulating knowledge from previous runs, including prompts, playbooks, optimizer code, and decision cadences. A meta‑agent rewrites and archives these policies, enabling reusable procedures and code that adapt to new tasks. Across multiple generations and tasks, RSI‑Opt improves optimizer performance, achieving higher z‑scores on evolution suites, better cross‑model transfer, and significant error reductions on PDE benchmarks compared to fixed‑prompt baselines.
The paper reviews 194 papers on using artificial intelligence to optimize data center energy use, coding 63 of them. It finds that most control studies validate only in simulation, none consider water withdrawal or embodied carbon, and savings estimates overlap across methods, preventing ranking. The authors propose CLEAR‑DC, a framework that links control and workload demand through elasticity, reports net benefits, and records energy, carbon, water, embodied share, and validation venue.
arXiv:2607. 12856v1 Announce Type: new Abstract: Buildings are expected to shift cooling loads in response to grid conditions.
The paper introduces ARTEMIS, a no-code evolutionary optimization platform that automatically tunes large language model (LLM) agents by jointly optimizing prompts, tool descriptions, and parameters using semantically-aware genetic operators. Starting from a benchmark script and natural language goals, ARTEMIS discovers configurable components, extracts performance signals from execution logs, and evolves configurations without architectural changes. Experiments on four agent systems show significant gains: a 13.6% increase in acceptance rate for the ALE Agent, a 10.1% performance boost for the Mini‑SWE Agent, a 36.9% token‑reduction for the CrewAI Agent, and a 22% accuracy improvement for the MathTales‑Teacher Agent using a smaller open‑source model.
arXiv:2607. 04577v1 Announce Type: new Abstract: Code models strictly prioritize functional correctness, leaving software energy efficiency as an unoptimized byproduct.
DecompGym is a benchmark that tests large language model agents on designing Benders decomposition and column generation algorithms. The benchmark contains 81 instances across nine problem families, requiring agents to produce solvers that run within 60 seconds, pass a method audit by an LLM judge, and achieve an objective within 1% of the optimal value. Evaluation of 12 GPT, Claude, and Gemini models shows that while some models solve all instances on the first try, many fail due to missing or suboptimal solutions, and reflection-based debugging improves success rates compared to simple regeneration.