token usage optimization

This study addresses the limitations of large language model (LLM)-based multi-agent systems in software engineering, particularly the lack of transparency in resource consumption, unpredictability of costs, and unclear environmental impact. To this end, it introduces the first standardized token consumption evaluation framework tailored for agent-based software engineering. By analyzing execution trajectories from the ChatDev framework across 30 development tasks, the work maps internal agent interactions to standard software engineering phases—design, coding, completion, code review, testing, and documentation—and quantifies the distribution of input, output, and reasoning tokens across these stages. The analysis reveals that the code review phase alone accounts for 59.4% of total token usage, with input tokens comprising 53.9% of the total, indicating that cost is primarily driven by automated refinement and validation rather than initial code generation. These findings provide empirical foundations for optimizing workflows, forecasting costs, and designing efficient agent collaboration protocols.

This study addresses the absence of a systematic, reusable, and empirically grounded end-to-end approach that integrates incentive mechanisms, governance structures, and tokenomics in current token economic designs. To bridge this gap, the paper proposes the Token Economic Design Method (TEDM), which, for the first time, unifies these three dimensions into a structured and actionable design framework, with explicit emphasis on sociotechnical context and early-stage design considerations. Developed through the design science research paradigm and informed by qualitative synthesis, co-design case studies, and expert interviews, TEDM was empirically validated through its application to the Currynomics stablecoin ecosystem and subsequent expert evaluation. The results demonstrate that TEDM effectively supports the analysis and construction of tokenized ecosystems, offering practical and reusable design guidance.

This study addresses the lack of systematic modeling approaches for token economies and quantitative analysis of event impacts. Building upon the DeTEcT framework, it proposes the first integrated methodology that combines formal token economy simulation with significance-based measurement of event effects. By introducing an event impact analysis framework augmented with numerical simulation techniques and wealth distribution metrics, the work enables quantitative assessment of wealth redistribution effects triggered by endogenous policy changes—such as Bitcoin Improvement Proposals (BIPs). Using Bitcoin as a case study, the approach demonstrates its effectiveness and practicality in capturing economic dynamics and evaluating the consequences of significant protocol-level events.

Current generative AI platforms strictly bind user-purchased tokens to specific timeframes, accounts, and services, significantly limiting usage flexibility. Drawing on MacLean et al.’s (1991) design space analysis framework, this study systematically examines the terms of service of ChatGPT, Claude, Gemini, and Grok, reconceptualizing tokens not merely as techno-economic units but as a design element for user empowerment. The work introduces the concept of “token usage transferability” and identifies five design axes—Target, Direction, Unit, Control, and Reversibility—defining five distinct types of transferability: carry-over, co-management, transfer, conversion, and trade. This framework offers a systematic design blueprint to enhance user autonomy in generative AI ecosystems.

Current automated market maker (AMM) designs lack a unified taxonomy and standardized evaluation criteria, resulting in elevated financial risk, suboptimal capital efficiency, and poor cross-domain adaptability. To address this, we propose the first systematic AMM taxonomy framework, integrating mechanism design, game-theoretic analysis, and software engineering principles to establish a verifiable and extensible modeling and comparative paradigm. Leveraging this framework, we design three AMM prototypes—each formally aligned with core token issuance and exchange requirements—thereby bridging the disciplinary gap between economic modeling and systems implementation. Our contributions include: (i) a rigorous, modular classification schema enabling principled AMM analysis; (ii) executable, specification-driven prototypes supporting formal verification; and (iii) a structured design methodology for developers, facilitating robust, multi-scenario deployment and advancing the engineering of sustainable cryptographic economies. (149 words)

This study addresses the unpredictable token consumption caused by context inflation during the execution of large language model (LLM) agents. To tackle this issue, we propose a segmented and composable cost modeling approach that constructs composable cost representations by integrating context growth records with a dynamic evidence fusion algorithm. Through cumulative estimation and dynamic updating mechanisms, the method achieves precise real-time prediction without requiring additional LLM invocations. Experimental results demonstrate that our approach reduces the average prediction error by 14.5% and saves 21.3% in token consumption under budget constraints, while maintaining a single-prediction latency of only 32.8 milliseconds. These findings indicate that the proposed method effectively balances computational efficiency with predictive accuracy for resource-aware agent deployment.

This study addresses the sustainability challenges faced by operators due to cost-benefit mismatches and price volatility in AI services. To manage such uncertainty, it proposes a structured contract infrastructure that decouples service consumption rights from payment collection rights. Methodologically, this work pioneers the introduction of financial derivatives logic into the AI computing market, enabling standardized commitments and risk hedging across heterogeneous services. Furthermore, it leverages smart contracts to formalize participant roles, ownership structures, and settlement rules, validating system logic through API replay. Experimental results demonstrate that forward contracts effectively reduce average expenditures, while financing mechanisms significantly enhance user contributions under low-capital conditions.

This study addresses the challenge of quantifying the complexity and cost induced by external requirement changes when detailed knowledge of a system’s internal logic is unavailable. To this end, the authors propose a black-box assessment method based on a directed graph of component coupling. By analyzing component interfaces and integrating multi-view modeling—graphical, algebraic, and tabular—the approach uniquely links interface characteristics to cost factors, enabling computable bounded estimates of change-induced complexity and associated costs. The method was validated through a large-scale integration case in a retail banking platform, demonstrating its effectiveness and providing architects and operations teams with actionable, quantitative insights for system design and maintenance.

This study addresses a critical gap in blockchain research, which has predominantly focused on on-chain transactions while neglecting the comprehensive lifecycle management of cryptographic assets. For the first time, the paper introduces the ISO 15489-1:2016 records management standard into the blockchain domain, leveraging records lifecycle theory to propose a seven-stage data lifecycle framework spanning from creation to disposition. The applicability of this model is demonstrated through case studies involving Bitcoin, fungible tokens, and non-fungible tokens. By elucidating the inherent characteristics of blockchain as a records management system, the framework clarifies the boundaries between on-chain and off-chain data and examines how privacy-enhancing technologies affect lifecycle visibility. This structured perspective offers valuable insights for the governance of crypto-assets, regulatory compliance, and forensic investigations.

This study addresses the prevalent conflation of on-chain transfer volume with the liquidity of tokenized real-world assets (RWAs). Raw transaction data frequently conflates non-trading operations, such as minting and burning, with genuine economic activity, while intermediary addresses severely distort ownership concentration metrics. Leveraging Ethereum on-chain data, this work introduces an event classification algorithm to systematically isolate non-economic transfers and reconstructs turnover rates and concentration indices by comparing metrics before and after intermediary removal. Results demonstrate that transfer classification substantially alters turnover estimates, and excluding intermediaries paradoxically increases concentration among remaining addresses. By exposing the measurement biases inherent in conventional on-chain metrics within the RWA domain, this research establishes a novel paradigm for accurately assessing true market liquidity.