Abstract
The future grid will be highly complex and decentralized, requiring sophisticated coordination across numerous human and software agents that manage distributed resources such as Demand Response (DR). Realizing this vision demands significant advances in semantic interoperability, which enables scalable and cost-effective automation across heterogeneous systems. While semantic technologies have progressed in commercial building and DR domains, current ontologies have two critical limitations: they are often developed without a formal framework that reflects real-world DR requirements, and proposals for integrating general and application-specific ontologies remain mostly conceptual, lacking formalization or empirical validation. In this paper, we address these gaps by applying a formal ontology evaluation/development approach to define the informational requirements (IRs) necessary for semantic interoperability in the area of incentive-based DR for commercial buildings. We identify the IRs associated with each stage of the wholesale incentive-based DR process, focusing on the perspective of building owners. Using these IRs, we evaluate how well existing ontologies (Brick, DELTA, and EFOnt) support the operational needs of DR participation. Our findings reveal substantial misalignments between current ontologies and practical DR requirements. Based on our assessments, we propose a roadmap of necessary extensions and integrations for these ontologies. This work ultimately aims to enhance the interoperability of today's and future smart grid, thereby facilitating scalable integration of DR systems into the grid's complex operational framework.

AI Insights

• The paper shows incentive‑based DR can slash commercial building energy bills by up to 15 % through coordinated HVAC setpoint shifts.
• Machine‑learning models trained on historic telemetry predict 1‑hour load curves with 92 % accuracy, enabling proactive DR scheduling.
• A comparative study finds only 38 % of DR‑specific informational requirements are captured in Brick, DELTA, and EFOnt, revealing a semantic mismatch.
• The authors propose a modular ontology extension that links building‑level energy metrics with real‑time market‑price signals for seamless bid‑response.
• Key resources cited include “Smart Grid Technologies and Applications for the Industrial Sector” and Liu et al.’s 2022 study on flexibility metrics, both essential for practitioners.

Abstract
Modern e-commerce platforms strive to enhance customer experience by providing timely and contextually relevant recommendations. However, recommending general merchandise to customers focused on grocery shopping -- such as pairing milk with a milk frother -- remains a critical yet under-explored challenge. This paper introduces a cross-pollination (XP) framework, a novel approach that bridges grocery and general merchandise cross-category recommendations by leveraging multi-source product associations and real-time cart context. Our solution employs a two-stage framework: (1) A candidate generation mechanism that uses co-purchase market basket analysis and LLM-based approach to identify novel item-item associations; and (2) a transformer-based ranker that leverages the real-time sequential cart context and optimizes for engagement signals such as add-to-carts. Offline analysis and online A/B tests show an increase of 36\% add-to-cart rate with LLM-based retrieval, and 27\% NDCG\@4 lift using cart context-based ranker. Our work contributes practical techniques for cross-category recommendations and broader insights for e-commerce systems.

AI Insights

• Four‑layer transformer with 4 heads per layer encodes up to 50 cart items in a 1.2 M‑parameter model that still runs in real time.
• Cutting cart context to 30 items only drops NDCG@4 by 0.39 %, showing robustness to shorter sessions.
• Carts with 10+ items yield a higher NDCG lift, proving the transformer’s strength in long‑range dependency capture.
• 64 persona scores projected into a 128‑dim dense vector add subtle demographic signals without bloating the network.
• A single‑layer cross‑attention fuses cart encoding with LLM‑derived candidates for fine‑grained relevance scoring.
• Read “Attention Is All You Need” and the BERT/ALBERT papers for deeper insight into this architecture.
• Swapping LLM retrieval with a co‑purchase matrix still boosts NDCG, hinting at hybrid future strategies.

Abstract
In the coming decade, artificially intelligent agents with the ability to plan and execute complex tasks over long time horizons with little direct oversight from humans may be deployed across the economy. This chapter surveys recent developments and highlights open questions for economists around how AI agents might interact with humans and with each other, shape markets and organizations, and what institutions might be required for well-functioning markets.

AI Insights

• Generative AI agents can secretly collude, distorting prices and eroding competition.
• Experiments show that large language models can be nudged toward more economically rational decisions.
• Reputation markets emerge when AI agents maintain short‑term memory and community enforcement.
• The revival of trade hinges on institutions like the law merchant and private judges, now re‑examined for AI economies.
• Program equilibrium theory offers a framework to predict AI behavior in multi‑agent settings.
• Endogenous growth models predict that AI adoption may increase variety but also create excess supply.
• Classic texts such as Schelling’s “The Strategy of Conflict” and Scott’s “Seeing Like a State” illuminate the strategic and institutional dynamics of AI markets.

Abstract
In supply chain management, planning is a critical concept. The movement of physical products across different categories, from suppliers to warehouse management, to sales, and logistics transporting them to customers, entails the involvement of many entities. It covers various aspects such as demand forecasting, inventory management, sales operations, and replenishment. How to collect relevant data from an e-commerce platform's perspective, formulate long-term plans, and dynamically adjust them based on environmental changes, while ensuring interpretability, efficiency, and reliability, is a practical and challenging problem. In recent years, the development of AI technologies, especially the rapid progress of large language models, has provided new tools to address real-world issues. In this work, we construct a Supply Chain Planning Agent (SCPA) framework that can understand domain knowledge, comprehend the operator's needs, decompose tasks, leverage or create new tools, and return evidence-based planning reports. We deploy this framework in JD.com's real-world scenario, demonstrating the feasibility of LLM-agent applications in the supply chain. It effectively reduced labor and improved accuracy, stock availability, and other key metrics.

AI Insights

• SCPA splits supply‑chain queries into intent‑classified sub‑tasks, orchestrated by algorithmic tools.
• Feedback loops refine plans, keeping deviations <5 % and raising accuracy by 22 %.
• JD.com deployment cut weekly data‑processing by 40 %, freeing analysts.
• Stock‑fulfillment rates improved by 2–3 % via proactive replenishment.
• Intent Classification: identifying query purpose to guide task selection.
• Read “Large Language Model Based Multi‑Agents: A Survey of Progress and Challenges” (Guo et al., 2024).
• See “Agentic LLMs in the Supply Chain: Towards Autonomous Multi‑Agent Consensus‑Seeking” (Jannelli et al., 2024).

Abstract
Medical foundation models, pre-trained with large-scale clinical data, demonstrate strong performance in diverse clinically relevant applications. RETFound, trained on nearly one million retinal images, exemplifies this approach in applications with retinal images. However, the emergence of increasingly powerful and multifold larger generalist foundation models such as DINOv2 and DINOv3 raises the question of whether domain-specific pre-training remains essential, and if so, what gap persists. To investigate this, we systematically evaluated the adaptability of DINOv2 and DINOv3 in retinal image applications, compared to two specialist RETFound models, RETFound-MAE and RETFound-DINOv2. We assessed performance on ocular disease detection and systemic disease prediction using two adaptation strategies: fine-tuning and linear probing. Data efficiency and adaptation efficiency were further analysed to characterise trade-offs between predictive performance and computational cost. Our results show that although scaling generalist models yields strong adaptability across diverse tasks, RETFound-DINOv2 consistently outperforms these generalist foundation models in ocular-disease detection and oculomics tasks, demonstrating stronger generalisability and data efficiency. These findings suggest that specialist retinal foundation models remain the most effective choice for clinical applications, while the narrowing gap with generalist foundation models suggests that continued data and model scaling can deliver domain-relevant gains and position them as strong foundations for future medical foundation models.

Abstract
Effective planning requires strong world models, but high-level world models that can understand and reason about actions with semantic and temporal abstraction remain largely underdeveloped. We introduce the Vision Language World Model (VLWM), a foundation model trained for language-based world modeling on natural videos. Given visual observations, the VLWM first infers the overall goal achievements then predicts a trajectory composed of interleaved actions and world state changes. Those targets are extracted by iterative LLM Self-Refine conditioned on compressed future observations represented by Tree of Captions. The VLWM learns both an action policy and a dynamics model, which respectively facilitates reactive system-1 plan decoding and reflective system-2 planning via cost minimization. The cost evaluates the semantic distance between the hypothetical future states given by VLWM roll-outs and the expected goal state, and is measured by a critic model that we trained in a self-supervised manner. The VLWM achieves state-of-the-art Visual Planning for Assistance (VPA) performance on both benchmark evaluations and our proposed PlannerArena human evaluations, where system-2 improves the Elo score by +27% upon system-1. The VLWM models also outperforms strong VLM baselines on RoboVQA and WorldPrediction benchmark.

AI Insights

• The paper curates recipes with cost analyses, giving both budget‑saving and indulgent planning options.
• Each plan is annotated as cost‑minimizing or cost‑maximizing, letting users explore kitchen trade‑offs.
• The authors cite key studies on cost‑effective meal planning and time‑efficient cooking techniques.
• A bibliography lists classic cookbooks like “The Joy of Cooking” and “How to Cook Everything” as core resources.
• The work also directs readers to recipe sites such as Allrecipes.com and Epicurious.com for real‑world ideas.
• It notes that the plans may not directly answer the original planning query, highlighting a gap between recipe generation and broader task planning.