LLMs are being deployed in weather forecasting, greenhouse control, waste management, trading and scientific calibration, with specialized benchmarks and pilots surfacing both gains and limitations. Stress tests reveal that generalist models can degrade under complex domain-specific conditions.
Backtrader-Bench introduces two pipelines to evaluate LLM agents in algorithmic trading: one generates multiple-choice questions from backtest configurations with independent verification, the other mines harder questions that require code execution....
Distribird is an agentic application that automates the construction of Bayesian priors from the literature, running entirely locally on open-weight models. Evaluated on 24 parameters across 10 domains, the multi-agent pipeline matches a single-promp...
Two LLM agents with opposing goals don't compete—they collapse. Experience Orchestrator, tested across 60,000 financial services simulations, adds a control layer using a Contextual Bandit, PID, and POMDP. High-intent advisor contact rate rises from ...
A study of 28,592 French headlines shows LLMs reliably detect conflict and strategic-game frames but struggle with normative judgments. The findings guide the design of local annotation pipelines that separate robust from fragile constructs, mitigati...
A closed-loop system driven by an LLM that processes data from 49 phytosensors and directly controls lighting and microclimate autonomously optimized a vertical farm. The model cut the production cycle by 35% and uncovered an unlikely strategy – dark...
A dedicated benchmark tests 33 large language models on solid waste management tasks. The best model hits nearly 95% accuracy on easy questions, but on hard ones the average drops to 42.5%. Calculation, experimental design, and urban planning remain ...
A new evaluation framework pairs a unified taxonomy benchmark with self-adaptive multimodal fuzzing (SAMF) and shows that state-of-the-art MLLMs degrade under stress, revealing a gap between reasoning and factual grounding. RL alignment even worsens ...
An open model from DeepMind, published in Nature, improves cyclone forecasts by an extra day, but the real surprise is that it runs on a single NVIDIA H100. The code is on GitHub, marking a turning point for local inference of complex weather models.
