4arXiv cs.AI (Artificial Intelligence)·
Tutorial on LLM and agentic AI architectures for smart grid applications with solver-grounded design principle
A new arXiv preprint presents a tutorial on applying LLMs and agentic AI systems to power grid tasks including wind forecasting, EV charging scheduling, power flow analysis, and contingency diagnosis. The paper proposes a 'solver-grounded' design principle where numerical outputs are only reported when they originate from a trusted external solver and pass explicit verification, addressing the problem of LLMs producing physically infeasible outputs. Four case studies compare LLM-only baselines against solver-grounded agents, with EVAgent reducing unmet energy by 7.5-9.5x and GridDebugAgent repairing 17/39 contingency cases while cutting violations by 52.3%. A four-group evaluation framework covering task utility, solver correctness, faithfulness, and cost/latency is also proposed.
Related guides (2)
Related events (8)
Tutorial and survey on LLM-powered agentic AI for 5G/6G network control and management
A two-part tutorial-and-survey paper formalizes the application of LLM-based agentic AI to 5G and 6G network architectures, covering reasoning, planning, tool use, and multi-agent coordination mapped onto telecom control planes. The work addresses a gap in existing literature by integrating protocol-level detail, evaluation frameworks, and standardization alignment. It surveys major 6G initiatives and identifies open challenges for autonomous telecommunications. The paper targets researchers and practitioners at the intersection of AI agents and next-generation network infrastructure.
Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents
Agentic CLEAR is an automatic evaluation framework for LLM-based agentic systems that analyzes behavior at three granularity levels: system, trace, and node. Unlike existing tools that rely on static error taxonomies or focus only on observability, it dynamically generates textual insights and integrates above the observability layer with an accessible UI. Experiments across four benchmarks and seven agentic settings demonstrate strong alignment with human-annotated errors and predictive accuracy for task success rates.
Survey: LLMs for front-end EDA — HDL generation, testbench construction, and agentic design automation
A new arXiv survey reviews the application of large language models to front-end chip design tasks, including hardware description language (HDL) generation, testbench construction, and high-level synthesis optimization. The paper traces the evolution from LLMs as localized assistants toward autonomous agentic EDA systems, citing OpenClaw as a representative pioneering system. It identifies key challenges and outlines future opportunities for agentic AI in electronic design automation.
Survey: Agentic Environment Engineering for LLMs — Modeling, Synthesis, Evaluation, and Application
A comprehensive arXiv survey systematically reviews the design and engineering of interactive environments for LLM-based agents, covering the full lifecycle from environment modeling and synthesis to evaluation and application. The paper categorizes environments across eight attributes and eight domains, introduces symbolic and neural synthesis paradigms, and characterizes four pathways for agent-environment co-evolution including memory-centric, orchestration-centric, trajectory-centric, and exploration-centric approaches. It also identifies three paradigms of environment evolution (neural-driven, difficulty-driven, scaling-driven) and proposes future directions such as Environment-as-a-Service and multi-agent environments. This is a reference-organizing contribution for the rapidly growing agent tooling and evaluation space.
Agentic LLM collectives proposed as interpretable substrates for Artificial Life research
A preprint from arXiv argues that populations of agentic LLMs — equipped with persistent memory, tools, and autonomous action — can serve as a computational substrate for Artificial Life (ALife) research. The key claim is that because agents communicate in natural language, their collective emergent behaviors are directly interpretable by examining textual traces or querying the agents themselves. The paper extends existing notions of LLM interpretability to multi-agent collectives and surveys recent examples of agentic LLM systems in both controlled and deployed settings. This positions multi-agent LLM systems as a novel lens for studying emergence and complexity while retaining interpretability.
Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches
This paper introduces an agentic framework where an LLM acts as an operations research expert, translating natural-language user prompts into structured updates ('patches') to deployed optimization models and selecting appropriate re-optimization techniques from a toolbox. The toolbox leverages primal information—historical solutions, valid inequalities, solver configurations, and metaheuristics—to accelerate re-optimization while preserving solution quality. Experiments on supply chain re-optimization and university exam scheduling demonstrate computational efficiency gains and improved interpretability through patch-based model modifications. The framework aims to reduce dependence on OR experts for maintaining dynamic decision-support systems.
MyAG: Graph-based framework for composable LLM agent system design and analysis
Researchers introduce MyAG, an open-source framework that structures LLM agent systems using three graph abstractions: a component graph, a workflow graph, and a search graph for runtime execution. The separation enables flexible component reuse across different execution strategies, with support for hierarchical composition via recursive system nodes and built-in monitoring and visualization tools. Experiments on representative agent applications demonstrate performance-efficiency tradeoff analysis capabilities.
SolarChain-Eval: Physics-constrained benchmark for trustworthy AI agents in decentralized energy markets
Researchers introduce SolarChain-Eval, a benchmark for evaluating autonomous economic agents in decentralized energy markets under physical constraints. The benchmark formulates market governance as a Gymnasium-compatible MDP and assesses policies across market utility, physical safety, slippage, fairness, and auditability dimensions. An LLM-based Planner/Auditor layer is incorporated to constrain and log agent actions; experiments reveal a utility-safety trade-off where RL agents improve market utility but can still produce unsafe behavior, and the LLM layer cannot compensate for a misspecified reward function. Code and data are released open-access.