artificial intelligence

Permission to Retry: A Study of Authorization and Recovery in AI Agent Workflows

A finite conformance study that checks checkpoint state, permission to dispatch, evidence of an external effect and permission to reconcile are distinct obligations through histories scored against a provider effect ledger hidden from the recovering application.

TACS-RF: Tool-driven Agentic Circuit Synthesis of RF and mmWave Modules

The agent-driven design flow and the resulting division of labor between human and agent is described, taking a step toward a"text-to-ASIC"future for designing RF/mmWave hardware.

Don't Forget What You Just Learned: Self-Directed Repair Turns Agent Mistakes Into Lasting Lessons

Self-Direction is introduced, a mechanism for agents to learn from mistakes that combines the benefits of temporary in-context retries and policy updates and reduces repeated mistakes across future encounters of a task, nearly doubling the reliability of an agent's corrections.

PaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean

PaperFormalizer, a Lean-based agentic pipeline that helps authors find and close small gaps in their own papers and turn each paper into a Lean-verified version, aims to make research that rests on mathematical proofs more robust.

Patronizing and Condescending Language Detection in English and Mandarin

This paper proposes a system for the automated detection of PCL, which uses static word embeddings and a convolutional neural network for classification, while the second approach uses pre-trained BERT embeddings fine-tuned for the PCL task.

Phronix: The Capability-Centric Learning Paradigm for Agents

Phronix is introduced, a capability-centric learning paradigm that enables agentic harnesses to acquire, validate, and refine reusable capabilities from their own executions, significantly reducing solution non-determinism and improving reliability.

Tradeoff-Aware Territory Design: A Multi-Objective Decision System for Enterprise Customer-to-Seller Allocation

Enterprise customer journeys are shaped not only by product experiences and marketing, but also by recurring resource-allocation decisions. In B2B go-to-market (GTM) organizations, territory carving determines which accounts receive seller coverage, which seller-account relationships are preserved, and how limited fiel...

Integrated Pest Management Models for Sustainable Agriculture: Principles, Applications, and Future Directions

Integrated Pest Management (IPM) has become an important approach for protecting crops while reducing the environmental and health concerns associated with excessive pesticide use. Conventional pest control often depends heavily on chemical pesticides, which can contribute to pesticide resistance, pest resurgence, cont...

Extended Reality, Telementoring, and Artificial Intelligence-Assisted Assessment in Surgical Training: A Narrative Review

Robots for CT-guided needle insertion: clinical implementation and future perspectives

Abstract Robotic systems for computed tomography (CT)-guided needle insertion have been developed to address the limitations of conventional manual needle insertion. Thus far, various robotic systems have been clinically implemented, and accumulating evidence has suggested their clinical utility. The evidence has evolv...

Decentralizing Cybersecurity across Artificial Intelligence, Internet of Things, Blockchain, Machine Learning, and Agentic AI: A Systematic Literature Review

3状態Blume--Capel選挙ポテンシャルゲームにおける非同期ショックカスケード、スピノーダル・ヒステリシス、および空間感染米国50州にわたる歴史的分割議会バックテストとマルチレジーム・モンテカルロ検証

アブストラクト 二大政党得票率 $R_{k}=\frac{1}{2}(1+m_{k}^{*}/q_{k}^{*})$ を逆転させることが確認された。2018〜2020年のねじれ議会に対する歴史的バックテストからは、上院による制度的緩衝作用と急速な記憶散逸が、高投票率かつ順序可換な均衡($q_{k}^{*}>84\%$)を維持することが確認される。対照的に、緩衝作用のない両院の膠着状態の下...