arXiv subjects

Haotian Ren

Publications and source records attributed to Haotian Ren.

5 recordsLinked to original sources

arXiv2025

MemEvolve: Meta-Evolution of Agent Memory Systems

Self-evolving memory systems are unprecedentedly reshaping the evolutionary paradigm of large language model (LLM)-based agents. Prior work has predominantly relied on manually engineered memory architectures to store trajectories, distill experience, and synthesize reusable tools, enabling agents to evolve on the fly within environment interactions. However, this paradigm is fundamentally constrained by the staticity of the memory system itself: while memory facilitates agent-level evolving, the underlying memory architecture cannot be meta-adapted to diverse task contexts. To address this gap, we propose MemEvolve, a meta-evolutionary framework that jointly evolves agents' experiential knowledge and their memory architecture, allowing agent systems not only to accumulate experience but also to progressively refine how they learn from it. To ground MemEvolve in prior research and foster openness in future self-evolving systems, we introduce EvolveLab, a unified self-evolving memory codebase that distills twelve representative memory systems into a modular design space (encode, store, retrieve, manage), providing both a standardized implementation substrate and a fair experimental arena. Extensive evaluations on four challenging agentic benchmarks demonstrate that MemEvolve achieves (I) substantial performance gains, improving frameworks such as SmolAgent and Flash-Searcher by up to $17.06\%$; and (II) strong cross-task and cross-LLM generalization, designing memory architectures that transfer effectively across diverse benchmarks and backbone models.

cs.CL↗

arXiv2023

Multi-label Learning from Privacy-Label

Multi-abel Learning (MLL) often involves the assignment of multiple relevant labels to each instance, which can lead to the leakage of sensitive information (such as smoking, diseases, etc.) about the instances. However, existing MLL suffer from failures in protection for sensitive information. In this paper, we propose a novel setting named Multi-Label Learning from Privacy-Label (MLLPL), which Concealing Labels via Privacy-Label Unit (CLPLU). Specifically, during the labeling phase, each privacy-label is randomly combined with a non-privacy label to form a Privacy-Label Unit (PLU). If any label within a PLU is positive, the unit is labeled as positive; otherwise, it is labeled negative, as shown in Figure 1. PLU ensures that only non-privacy labels are appear in the label set, while the privacy-labels remain concealed. Moreover, we further propose a Privacy-Label Unit Loss (PLUL) to learn the optimal classifier by minimizing the empirical risk of PLU. Experimental results on multiple benchmark datasets demonstrate the effectiveness and superiority of the proposed method.

cs.LG↗

arXiv2023

Runtime Stealthy Perception Attacks against DNN-based Adaptive Cruise Control Systems

Adaptive Cruise Control (ACC) is a widely used driver assistance technology for maintaining the desired speed and safe distance to the leading vehicle. This paper evaluates the security of the deep neural network (DNN) based ACC systems under runtime stealthy perception attacks that strategically inject perturbations into camera data to cause forward collisions. We present a context-aware strategy for the selection of the most critical times for triggering the attacks and a novel optimization-based method for the adaptive generation of image perturbations at runtime. We evaluate the effectiveness of the proposed attack using an actual vehicle, a publicly available driving dataset, and a realistic simulation platform with the control software from a production ACC system, a physical-world driving simulator, and interventions by the human driver and safety features such as Advanced Emergency Braking System (AEBS). Experimental results show that the proposed attack achieves 142.9 times higher success rate in causing hazards and 82.6% higher evasion rate than baselines, while being stealthy and robust to real-world factors and dynamic changes in the environment. This study highlights the role of human drivers and basic safety mechanisms in preventing attacks.

cs.CR↗

arXiv2022

Design and Validation of an Open-Source Closed-Loop Testbed for Artificial Pancreas Systems

The development of a fully autonomous artificial pancreas system (APS) to independently regulate the glucose levels of a patient with Type 1 diabetes has been a long-standing goal of diabetes research. A significant barrier to progress is the difficulty of testing new control algorithms and safety features, since clinical trials are time- and resource-intensive. To facilitate ease of validation, we propose an open-source APS testbed by integrating APS controllers with two state-of-the-art glucose simulators and a novel fault injection engine. The testbed is able to reproduce the blood glucose trajectories of real patients from a clinical trial conducted over six months. We evaluate the performance of two closed-loop control algorithms (OpenAPS and Basal Bolus) using the testbed and find that more advanced control algorithms are able to keep blood glucose in a safe region 93.49% and 79.46% of the time on average, compared with 66.18% of the time for the clinical trial. The fault injection engine simulates the real recalls and adverse events reported to the U.S. Food and Drug Administration (FDA) and demonstrates the resilience of the controller in hazardous conditions. We used the testbed to generate 25 years of synthetic data representing 20 different patient profiles with realistic adverse event scenarios, which would have been expensive and risky to collect in a clinical trial. The proposed testbed is a valid tool that can be used by the research community to demonstrate the effectiveness of different control algorithms and safety features for APS.

cs.SE↗

arXiv2022

Strategic Safety-Critical Attacks Against an Advanced Driver Assistance System

A growing number of vehicles are being transformed into semi-autonomous vehicles (Level 2 autonomy) by relying on advanced driver assistance systems (ADAS) to improve the driving experience. However, the increasing complexity and connectivity of ADAS expose the vehicles to safety-critical faults and attacks. This paper investigates the resilience of a widely-used ADAS against safety-critical attacks that target the control system at opportune times during different driving scenarios and cause accidents. Experimental results show that our proposed Context-Aware attacks can achieve an 83.4% success rate in causing hazards, 99.7% of which occur without any warnings. These results highlight the intolerance of ADAS to safety-critical attacks and the importance of timely interventions by human drivers or automated recovery mechanisms to prevent accidents.

cs.SE↗