arXiv subjects

Hailin Zhong

Publications and source records attributed to Hailin Zhong.

4 recordsLinked to original sources

arXiv2026

AI Harness: Certification under Proposal-Conditioned Information for Foundation-Model Agents

Foundation-model agents are often modeled as policies over an observed state. In deployed systems, however, a runtime may intervene only after the model has emitted a semantic proposal, making the proposal both an action candidate and a decision-time observation generated by a history-conditioned process. We show that collapsing this structure into a state-only proposal envelope can preserve proposal coverage while destroying certifiability. In a finite robust interface, the viability kernel of the collapsed model is contained in the physical projection of the history-augmented kernel, and the collapse is lossless exactly when every proposal-conditioned collapsed fiber retains a common robust-safe intervention. This gap can be maximal even with constant-size proposal and history alphabets. The same common-action condition yields a dual result: observing the current proposal can restore robust feasibility when it separates latent modes requiring incompatible interventions. We extend these one-step results over time using exact finite beliefs and standard safety and reachability fixed points, separating indefinite operational viability from finite worst-case verified progress. Controlled model-in-the-loop tests reproduce the predicted obstructions when telemetry or effect verification is removed or intervention authority is restricted. Thus, our contribution is not a new fixed-point calculus, but a characterization of when proposal--history correlation at the model--tool boundary is necessary for certification.

cs.AI↗

arXiv2026

AI Harness Engineering: A Runtime Substrate for Foundation-Model Software Agents

Foundation models have transformed automated code generation, yet autonomous software-engineering agents remain unreliable in realistic development settings. The dominant explanation locates this gap in model capability. We propose a different locus: software-engineering capability emerges from a model-harness-environment system, in which a runtime substrate -- the harness -- mediates how a foundation-model agent observes a project, acts on it, receives feedback, and establishes that a change is complete. We formalize this substrate as an AI Harness Engineering and identify eleven component responsibilities: task specification, context selection, tool access, project memory, task state, observability, failure attribution, verification, permissions, entropy auditing, and intervention recording. We operationalize the harness through a four-level ladder (H0-H3) that progressively exposes runtime support to the agent, and we propose a trace-based evaluation protocol that converts each agent run into an auditable episode package. Applied to a controlled validation task, the framework yields episode packages whose evidence structure varies systematically with harness level: lower levels produce only a final patch, higher levels produce reproduction logs, failure attributions, deterministic requirement checks, and structured verification reports. The framework reframes the central question of autonomous software engineering from whether a foundation model can produce a patch to whether the model-harness-environment system can produce a verifiably correct, attributed, and maintainable change. We outline a research program for the runtime systems that foundation-model software agents will require.

cs.SE↗

arXiv2025

GGBond: Growing Graph-Based AI-Agent Society for Socially-Aware Recommender Simulation

Current personalized recommender systems predominantly rely on static offline data for algorithm design and evaluation, significantly limiting their ability to capture long-term user preference evolution and social influence dynamics in real-world scenarios. To address this fundamental challenge, we propose a high-fidelity social simulation platform integrating human-like cognitive agents and dynamic social interactions to realistically simulate user behavior evolution under recommendation interventions. Specifically, the system comprises a population of Sim-User Agents, each equipped with a five-layer cognitive architecture that encapsulates key psychological mechanisms, including episodic memory, affective state transitions, adaptive preference learning, and dynamic trust-risk assessments. In particular, we innovatively introduce the Intimacy--Curiosity--Reciprocity--Risk (ICR2) motivational engine grounded in psychological and sociological theories, enabling more realistic user decision-making processes. Furthermore, we construct a multilayer heterogeneous social graph (GGBond Graph) supporting dynamic relational evolution, effectively modeling users' evolving social ties and trust dynamics based on interest similarity, personality alignment, and structural homophily. During system operation, agents autonomously respond to recommendations generated by typical recommender algorithms (e.g., Matrix Factorization, MultVAE, LightGCN), deciding whether to consume, rate, and share content while dynamically updating their internal states and social connections, thereby forming a stable, multi-round feedback loop. This innovative design transcends the limitations of traditional static datasets, providing a controlled, observable environment for evaluating long-term recommender effects.

cs.MA↗

arXiv2025

High-Efficiency Split Computing for Cooperative Edge Systems: A Novel Compressed Sensing Bottleneck

The advent of big data and AI has precipitated a demand for computational frameworks that ensure real-time performance, accuracy, and privacy. While edge computing mitigates latency and privacy concerns, its scalability is constrained by the resources of edge devices, thus prompting the adoption of split computing (SC) addresses these limitations. However, SC faces challenges in (1) efficient data transmission under bandwidth constraints and (2) balancing accuracy with real-time performance. To tackle these challenges, we propose a novel split computing architecture inspired by compressed sensing (CS) theory. At its core is the High-Efficiency Compressed Sensing Bottleneck (HECS-B), which incorporates an efficient compressed sensing autoencoder into the shallow layer of a deep neural network (DNN) to create a bottleneck layer using the knowledge distillation method. This bottleneck splits the DNN into a distributed model while efficiently compressing intermediate feature data, preserving critical information for seamless reconstruction in the cloud. Through rigorous theoretical analysis and extensive experimental validation in both simulated and real-world settings, we demonstrate the effectiveness of the proposed approach. Compared to state-of-the-art methods, our architecture reduces bandwidth utilization by 50%, maintains high accuracy, and achieves a 60% speed-up in computational efficiency. The results highlight significant improvements in bandwidth efficiency, processing speed, and model accuracy, underscoring the potential of HECS-B to bridge the gap between resource-constrained edge devices and computationally intensive cloud services.

cs.DC↗