The research, authored by Jun Yin of Beijing Cnoce Technologies Co., Ltd., addresses a persistent weakness in interactive intelligent systems. When requirements are complex, vague, or embedded in specialized background knowledge, conventional systems struggle to accurately interpret human needs or intentions. Rather than treating each user request as a one-shot prediction problem, the proposed algorithm treats interpretation as an iterative cycle: the system computes a response, collects real-time feedback about how well that response matched the demand, and continuously refines its behavior according to the demand response structure. The goal is to improve both the intelligent response capability of the system and the experience of the user on the other side of the interaction.

At the foundation of the method is an effective data collection mechanism. The system gathers real-time response information as interactions unfold, building up the raw material needed to evaluate and improve its own performance. In a known finite domain, the algorithm derives a corresponding feature statistical decision, which anchors the interpretation process in measurable properties of the data rather than in guesswork. This statistical grounding matters because human-computer cooperation networks are messy: nodes in such networks are not equally spaced or equally loaded, and the demands arriving at each node differ in both volume and character.

One of the paper’s central technical contributions lies in how it handles that unevenness. The algorithm extracts the load characteristics of non-equidistant nodes in the human-machine cooperation network using the knowledge of a large language model. In practical terms, the language model’s broad knowledge base is used to characterize how computational and communicative load is distributed across nodes that sit at irregular positions in the network topology. This allows the system to understand where demand concentrates, where it is sparse, and how those patterns shift as users interact with the system over time. Load characterization of this kind is essential for any cooperative system that must allocate responses fairly and quickly across many simultaneous users.

The second pillar of the method is attention. The algorithm constructs a knowledge framework for the large language model according to a two-level attention matrix, and then analyzes an iterative demand response strategy for human-machine cooperation in two stages. The two-level attention structure allows the model to weigh different pieces of information at different granularities, deciding which features of a request deserve emphasis and which contextual signals should modulate that emphasis. By organizing the response strategy into two stages, the system separates coarse interpretation from fine-grained refinement, letting each iteration pass progressively sharper approximations of user intent back into the loop.

The experimental results reported in the study offer concrete evidence that the design works as intended. The algorithm is able to remove abnormal data when the threshold is set to 10, and across three datasets the proportion of abnormal data reaches its lowest state under the proposed method. Anomaly removal at a fixed threshold is more than a housekeeping detail; noisy or malformed interaction data can poison the feedback loop that iterative systems depend on, so a reliable filtering stage protects the integrity of every subsequent optimization step. The fact that the algorithm achieves the lowest abnormal-data proportion across all three datasets suggests that the filtering mechanism is robust rather than tuned to a single data distribution.

Performance gains extend beyond data cleaning. After applying the algorithm, both throughput and utilization rate improved significantly, and the response speed became faster. Throughput measures how much useful work the system completes per unit of time, while utilization rate reflects how effectively the system’s resources are kept busy on productive tasks. Improvements in both metrics, combined with faster responses, indicate that the iterative loop does not merely reinterpret requests more accurately but also runs efficiently enough to lighten the operational burden on the underlying infrastructure. For users, faster response speed is the most visible benefit; for system operators, higher throughput and utilization translate directly into capacity savings.

The study situates itself within a growing body of work on human-machine cooperation. Prior research has explored cooperation between human operators and machines in scheduling problems, man-algorithm cooperation in the intelligent design of clothing products across multiple links, and collision-free path planning for industrial robot manipulators that must account for safe human-robot interaction. More recent efforts have examined how autonomous vehicles can assimilate human feedback in reinforcement learning models and how human-centric digital twins can support human-machine collaboration. What distinguishes the new algorithm is its explicit integration of large language model knowledge into the cooperation loop itself, rather than using language models only as peripheral interfaces.

That integration reflects a broader trend. Large language models have already been applied to domain-specific text mining, as demonstrated by materials-science language models built for information extraction, and to collaborative requirements elicitation, where human-machine iterative approaches use language models to help elicit and model software requirements. Natural language processing systems have been deployed to extract structured events from clinical texts and to classify sensitive records in mental healthcare. The new work extends this lineage into the domain of demand response, where the

Subject of Research: An iterative demand response algorithm that integrates large language model knowledge to improve human-computer cooperation in interpreting complex user requirements.

Article Title: Iterative Demand Response Algorithm for Human-Computer Cooperation Integrating Knowledge of Large Language Model

Article References: Iterative Demand Response Algorithm for Human-Computer Cooperation Integrating Knowledge of Large Language Model. (n.d.). https://doi.org/10.1007/s10489-026-07428-2

Image Credits: AI Generated

DOI: 10.1007/s10489-026-07428-2

Keywords: demand response algorithm, human-computer cooperation, large language model, iterative optimization, attention matrix, load characteristics, anomaly detection, throughput, utilization rate, user intent, Applied Intelligence, computational intelligence

The research, published in the Atlantic Economic Journal, develops a dynamic stochastic general equilibrium, or DSGE, framework — the workhorse modeling tool of modern macroeconomics — that for the first time integrates a sharing sector alongside two familiar pillars of household economics: market production and home production. In the model, households own stocks of physical capital, business firms own their own capital, and the sharing sector acts as a bridge between the market and the home. Crucially, the sharing economy uses household capital — the durable goods that families already own, such as vehicles and housing — to produce tradable services that compete with or complement conventional market output. This structural feature allows the authors to trace, shock by shock, how technological improvements ripple through an economy in which households can monetize their possessions.

The model’s central mechanism rests on the productive use of idle assets, one of the defining characteristics of platforms such as Airbnb and Uber. Rather than explicitly modeling two-sided marketplaces with matching algorithms and reputation systems — a level of detail that would render the framework intractable — the authors capture the efficiency of the sharing ecosystem through a utilization rate. This parameter, they caution, should not be read as a purely technological constant. Instead, it summarizes in reduced form how effectively existing household capital is converted into productive sharing services: a high utilization rate reflects better matching technologies, lower transaction costs, stronger platform intermediation and reputation systems, and more favorable institutional conditions, while a low rate signals frictions that prevent otherwise available assets from being actively shared.

Armed with this structure, the economists subject the model economy to three distinct types of technological disturbances and observe how output, investment, hours and consumption respond. The first experiment delivers a positive neutral technological shock to market production — the kind of economy-wide productivity gain that in standard models ignites a boom. The results are striking: business investment expands, but the accumulation of household durables is crowded out. Because capital and resources flow toward the market sector, both home production and sharing output decline. In other words, even a textbook market boom carries an unseen cost for the household side of the economy, as families divert resources away from the assets that feed their own production and their sharing activity.

The second shock reverses the direction: productivity improves inside the sharing economy itself, perhaps reflecting a better platform, cheaper transactions or more efficient matching of suppliers and users. Here the reallocation runs the opposite way. Investment in durables rises, but business capital investment falls, and with it market output and market hours. Households respond to the improved returns on sharing their assets by accumulating more durables and shifting effort toward monetizing them, drawing resources away from conventional employment and firm-level investment. A genuine technological revolution in the platform economy, the model suggests, is not neutral with respect to the rest of the macroeconomy — it visibly reallocates capital and labor across the market and household boundaries.

The third and perhaps most consequential experiment involves investment-specific technological shocks to durables — improvements that make household investment goods cheaper or better, analogous to declines in the quality-adjusted price of cars, appliances or home equipment. In earlier macroeconomic research, such shocks have posed a puzzle: they expand household capital at the expense of business capital, yet they do not appear to depress effective consumption in the data. The Málaga model offers a resolution. Because household capital simultaneously feeds two channels — home production and sharing activities — the expansion of the household capital stock sustains the consumption aggregate even as business investment contracts. The sharing economy, by giving household capital a second productive outlet, helps explain why cheaper durables do not translate into a visible consumption collapse.

Taken together, these results lead the authors to their headline conclusion: the sharing economy is countercyclical. When the market economy weakens, households mitigate the downturn by monetizing their durable assets, generating sharing output precisely when market income is under pressure. This buffer smooths aggregate consumption and, by extension, the business cycle itself. The finding resonates with a growing empirical literature on platform work and peer-to-peer markets — including studies of Uber drivers showing that flexible gig work carries substantial value for workers, and analyses of Airbnb quantifying how peer entry reshapes the accommodation industry — but it elevates those micro observations to the level of aggregate dynamics, where the sharing sector emerges as an implicit stabilizer.

The policy implications are significant. Modern stabilization policy — interest rate setting, fiscal stimulus, automatic stabilizers — is calibrated almost entirely against measured market activity. GDP, as national statisticians have long acknowledged, struggles to capture home production and has an uneasy relationship with the digital economy more broadly. If a substantial fraction of household adjustment to recessions now flows through channels that official statistics barely register, then observed market downturns may overstate the true welfare losses experienced by households, and conversely, market booms may overstate welfare gains that come at the cost of household-side activity. Central bankers and finance ministries designing business cycle stabilization policies, the authors argue, need to account for the sharing economy explicitly, because it both amplifies and transmits shocks through the household capital stock in ways that conventional models simply cannot see.

The study also connects to a deeper theoretical tradition. Household production entered formal macroeconomics decades ago, in influential work showing that the allocation of capital and time between market and home activities shapes aggregate fluctuations, and that household investment displays distinctive cyclical behavior — often leading business investment over the cycle. The sharing economy adds a third vertex to this market-home geometry, transforming household durables from a purely private input into a source of tradable services. As platforms lower transaction costs and raise the utilization rate of idle assets, the boundary between household capital and productive capital blurs further. The Málaga economists’ framework provides a tractable way to think about this transformation, and their conclusion is a provocative one: the quiet decisions of millions of households to rent out what they already own may constitute one of the most underappreciated shock absorbers in the modern economy.

Subject of Research: Macroeconomic modeling of the sharing economy's role in business cycle fluctuations and household capital allocation

Article Title: Sharing Economy and Technological Shocks over the Business Cycle

Article References: Sharing Economy and Technological Shocks over the Business Cycle. (n.d.). https://doi.org/10.1007/s11293-026-09860-8

Image Credits: AI Generated

DOI: 10.1007/s11293-026-09860-8

Keywords: sharing economy, business cycle, DSGE model, household capital, durable goods, home production, technological shocks, collaborative consumption, investment-specific technology, macroeconomic stabilization, peer-to-peer markets, utilization rate