System Optimization
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
SePO: Self-Evolving Prompt Agent for System Prompt Optimization
Announce Type: new Abstract: System prompt optimization improves agent behavior without modifying the underlying model, yielding human-readable, model-agnostic instructions. Existing methods build a prompt agent that refines task agents' system prompts, yet leave the prompt agent's own system prompt hand-engineered and fixed. We propose Self-Evolving Prompt Optimization (SePO), which treats the prompt agent's own system prompt as an optimization target alongside task agents' system prompts.
Recursive Jump Operators and Optimal Proof Systems
Announce Type: new Abstract: We study the relationship between the existence of optimal proof systems and recursive jump operators, two central open problems in proof complexity. For a set L, an optimal proof system is a strongest proof system in terms of proof length, whereas a recursive jump operator uniformly transforms any proof system for L into a stronger one with respect to proof length, thereby witnessing non-optimality. It is clear that the existence of a recursive jump operator for...
A Decentralized LiDAR-SLAM System with Certifiably Optimal Pose Graph Optimization
Announce Type: replace Abstract: Decentralized multi-robot LiDAR-SLAM is essential for collaborative missions but faces significant challenges in maintaining global consistency. Existing frameworks predominantly rely on local-search optimization or one-time coordinate alignment, which are prone to suboptimal convergence and long-term inconsistency, especially in large-scale or degenerate environments. To address these limitations, this paper presents the first decentralized LiDAR-SLAM system...
Clustering-enhanced adaptive Benders decomposition for energy systems planning optimization
arXiv:2606.00388v1 Announce Type: cross Abstract: High-resolution energy system capacity expansion models (CEMs) for energy transition planning often result in large-scale mixed-integer linear programming (MILP) formulations. Benders decomposition (BD) offers a scalable solution approach by iteratively solving a master problem (MP) for investment decisions and multiple subproblems (SPs) for operational decisions. However, accumulated Benders cuts generated by the SPs can make MP solution a...
Optimal transition in underdamped systems with memory
arXiv:2605.30897v1 Announce Type: new Abstract: Optimal finite-time control is essential for energy-efficient operation of nanoscale devices. While existing work has largely focused on transitions between equilibrium states in overdamped systems, many settings of practical interest -- including nanomechanical resonators, biomolecular conformational dynamics, and quantum Brownian motion -- are governed by underdamped dynamics where both particle inertia and frequency-dependent friction...
$H_2$ optimal model reduction of linear systems with multiple quadratic outputs
Announce Type: replace Abstract: In this work, we consider the $H_2$ optimal model reduction of dynamical systems that are linear in the state equation and up to quadratic nonlinearity in the output equation. As our primary theoretical contributions, we derive gradients of the squared $H_2$ system error with respect to the reduced model quantities and, from the stationary points of these gradients, introduce Gramian-based first-order necessary conditions for the $H_2$ optimal approximation...
Kore: Binary File Format Optimized for Modern Data Systems (Open Source)
The fastest, most compressed columnar format for big data | v0.1.0 KORE is a high-performance binary file format optimized for analytical workloads. It provides: - 38% compression ratio (vs 63% for Parquet) - 131x query speedup with column pruning & predicate pushdown - Zero data loss verification (400K+ cells tested) - Native Spark integration — read/write with PySpark Add this crate as a dependency (when published) or include from path: use kore_fileformat::*; // Write data...
A Multi-Agent System for IPMSM Design Optimization via an FEA-AI Hybrid Approach
arXiv:2606.09037v1 Announce Type: new Abstract: Interior permanent magnet synchronous motor (IPMSM) design requires balancing conflicting objectives and multi-physics constraints, while modern optimization workflows face three bottlenecks: manual problem setup, high finite element analysis (FEA) cost, and unreliable surrogate-based search in sparse or out-of-distribution regions. To address these limitations, we propose an end-to-end automated IPMSM design optimization framework that...
MASPOB: Bandit-Based Prompt Optimization for Multi-Agent Systems with Graph Neural Networks
arXiv:2603.02630v2 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved great success in many real-world applications, especially the one serving as the cognitive backbone of Multi-Agent Systems (MAS) to orchestrate complex workflows in practice. Since many deployment scenarios preclude MAS workflow modifications and its performance is highly sensitive to the input prompts, prompt optimization emerges as a more natural approach to improve its performance. However,...
Who Deserves the Reward? SHARP: Shapley Credit-based Optimization for Multi-Agent System
arXiv:2602.08335v2 Announce Type: replace Abstract: Integrating Large Language Models (LLMs) with external tools via multi-agent systems offers a promising new paradigm for decomposing and solving complex problems. However, training these systems remains notoriously difficult due to the credit assignment challenge, as it is often unclear which specific functional agent is responsible for the success or failure of decision trajectories. Existing methods typically rely on sparse or globally...