This work presents VeraGrid-Agent, a tool-augmented LLM that autonomously writes the simulator input, executes the open-source VeraGrid solver, and reads the solver output before answering, and does a failure-mode analysis to show that the few remaining errors arise from wrong interpretations during multi-step reasoning, rather than any failure in the simulators execution.
Abstract
Language models have demonstrated remarkable success in solving a wide range of tasks. However, answering complex scientific questions about the power flow often requires solving the distribution optimal power flow (D-OPF) problem. These questions call for numerical solvers and simulators, as linguistic reasoning from parametric knowledge often gives incorrect answers. In this work, we present VeraGrid-Agent, a tool-augmented LLM that autonomously writes the simulator input, executes the open-source VeraGrid solver, and reads the solver output before answering. To evaluate performance, we introduce VeraGrid-MCQ-150, a set of deterministic, expert template driven, $150$ multiple-choice questions. We evaluate the performance under two regimes: (i) no-tool reasoning and (ii) agent (LLM with simulator access). Without tools, every model performs with an accuracy of $42.7\%$--$49.3\%$. However, with VeraGrid-Agent, accuracy increases to $97.3\%$--$100.0\%$. We also do a failure-mode analysis to show that the few remaining errors arise from wrong interpretations during multi-step reasoning, rather than any failure in the simulators execution.
Large language models increasingly operate over large collections of tools, functions, APIs, and specialized agents. As the candidate action space grows, a function-calling model must process more schemas, consume more prompt tokens, and distinguish among increasingly similar or irrelevant alternatives. We study a complementary systems strategy: reduce the candidate set before language-model inference while leaving the downstream model unchanged. We introduce AgentWeave, a deterministic pre-inference routing layer that constructs a bounded model-visible action space using eligibility, requirement, capability, and routing signals. We evaluate AgentWeave with a frozen BFCL-derived routing-pressure protocol using the public MadeAgents/Hammer2.1-1.5b model. On 48 fresh BFCL V4 multiple-function tasks, AgentWeave achieves 6/48 (12.5%) native BFCL successes, whereas all-tools, deterministic random top-8, and semantic top-8 baselines each achieve 0/48. The paired success difference is +12.5 percentage points with a 10,000-resample paired bootstrap 95% confidence interval of +4.17 to +22.92 points and exact McNemar p=0.03125. Relative to all-tools exposure, AgentWeave presents 70.18% fewer tools, uses 61.70% fewer input tokens, and exhibits 50.95% lower mean local-model latency. The result is deliberately narrow: this is a BFCL-derived routing-pressure study rather than an official full BFCL leaderboard score, and absolute task success remains low. The evidence nevertheless shows that candidate-space construction can materially affect a fixed model's function-calling behavior and motivates evaluating routing as a distinct stage before model reasoning.
Saurav Singla, A. Singla, Advik Gupta et al.· 0 citations
A solver-grounded design principle is presented: a numerical result is reported only when it originates from a trusted tool and passes explicit verification, and a four-group evaluation framework spanning task utility, solver-grounded correctness, faithfulness and safe failure, and cost and latency is proposed.
Daniel Rojas, Abdulwahab Albassam, Aidan G. Leung et al.· 0 citations
Warehouse operations are governed by Standard Operating Procedures (SOPs) that encode complex, multi-system decision logic, which must be executed reliably under strict time constraints, yet LLM agents lack mechanisms to enforce procedural compliance and degrade under the context overload full SOP specifications introduce. We present Eluna, a production-deployed agentic system for reliable SOP execution. Eluna is a graph-guided, multi-agent framework that encodes SOPs as directed acyclic graphs with progressive disclosure and delegates independent tasks to parallel sub-agents, each with persistent code execution and live data access. To meet production latency and accuracy needs, we use asymmetric episodic distillation where a strong teacher is improved through episodic error memories, then a smaller student is fine-tuned on the corrected trajectories with memory stripped, internalizing corrections without inference-time overhead. On a 13-task benchmark and two production applications, our fine-tuned models match or exceed their teacher, beat all larger off-the-shelf baselines, and reach 94% expert agreement on the ticket processing application.
Ning Liu, Kalle Kujanpää, Zhaoxuan Zhu et al.· 1 citation
Complex systems, core objects of study in artificial life, model diverse phenomena through nonlinear, feedback-driven interactions that produce emergent behavior, with applications from population dynamics and biology to economic policy and strategic decision-making. Yet the difficulty of predicting how feedback structure gives rise to emergent behavior, a central open problem in artificial life, makes goal-directed design exceptionally challenging. In established practice, system structures are written in specialized modeling languages such as DYNAMO or STELLA, compounding the challenge with labor-intensive workflows that limit adoption and hinder timely decision-making. To address these challenges, we introduce CEDAR, an autonomous method that uses Large Language Model (LLM) agents to discover complex systems satisfying user-specified behavioral goals. Our key innovation is an LLM-driven Monte Carlo Tree Search (MCTS) deeply coupled with complex systems: at each iteration, an LLM Judge evaluates emergent behavior against specified goals and an LLM Editor proposes improved variants, with the Judge acting as a fitness function and the Editor as a variation operator, akin to a generate-and-evaluate loop in evolutionary computation. We represent complex systems as a restricted, runnable subset of Python with domain-specific primitives, letting LLMs modify system dynamics directly. CEDAR formalizes this as an MCTS variant with an LLM-parameterized transition kernel and value function, enabling goal-directed discovery of complex system behaviors while preserving solution diversity, and its LLM-based interpretability reveals how structural changes drive emergent behavior. CEDAR reduces human effort while enabling capabilities difficult to achieve with existing approaches, facilitating broader adoption of complex systems across domains.
A ScholForge - hierarchical multi-agent LLM system that tackles end-to-end software engineering research end-to-end, with a natural-language research goal, and produces working code, experimental results, and a compiled manuscript without human intervention.
A. Stepin, Boris Tolstokulakov, Vladislav Kulikov et al.· SIGSOFT FSE Companion· 0 citations
Ticket support in cloud services involves technical engineers using expert tools to resolve customer queries—% a process closely resembling information integration. To enhance both operational efficiency and resolution accuracy, we propose DualLane, a novel parallel dual-path planning architecture designed for AI agents. This framework adaptively manages the highly skewed frequency distribution characteristic of real-world user queries. For low-frequency long-tail scenarios, the slow path employs a two-stage planning mechanism that decouples task decomposition from parameter generation, effectively optimizing dependency propagation and reducing context complexity. In contrast, for high-frequency routine scenarios, the fast path bypasses expensive LLM-based full-plan generation by utilizing pre-validated execution templates, thereby improving response accuracy and reducing latency. After more than one year of extensive deployment in Alibaba Cloud's ECS production environment, DualLane has demonstrated remarkable robustness and stability. Offline benchmarks indicate a high accuracy rate of 96.5%, accompanied by superior latency performance. Crucially, online metrics reveal a median plan-execution latency of merely 4.2 seconds, with an agent-induced error rate maintained at a low 7.1%. These results underscore the practical viability and effectiveness of adaptive dual-path planning in large-scale, interactive AIOps systems.
Haoyu Wang, Wenxuan Ma, Bing Hu et al.· Proceedings of the 32nd ACM...· 0 citations