arXiv subjects

Yunfeng Bai

Publications and source records attributed to Yunfeng Bai.

8 recordsLinked to original sources

arXiv2026

An Empirical Study of Coordination Mode as the First-Class Citizen in From-Scratch Multi-Agent Coding

Multi-agent vibe coding promises to accelerate software development, yet existing benchmarks rely on synthetic environments that ignore practical time and monetary costs, conflate reasoning with communication, and reward only superficial completion. We introduce multi-agent from-scratch evaluation benchmark, MSEval, evaluating multi-agent coding on real-world tasks. Grounded in 10 authentic, full-stack projects across 10 domains, MSEval scores performance using hierarchical requirements and deterministic rubrics. Its execution engine, LegoGent, tests 10 collaboration topologies where agents coordinate via periodic sync intervals and deploy through native CI/CD pipelines. Concurrently, the automated grader TAgent dynamically probes implementations to jointly measure functional success, latency, and prefix-cached token cost. Across 100 runs, MSEval reveals that organizational topology rivals model capability in shaping the speed--cost--quality trade-off. For identical tasks and models, varying the topology shifts scores by over 30 points and doubles wall-clock time. Structured pipelines converge fastest with the highest quality, whereas heavy managerial oversight degrades performance. Ultimately, MSEval establishes a rigorous, reproducible standard for measuring how multi-agent teams actually build software. The benchmark is released at https://github.com/robinren03/MSEval.

cs.AI↗

arXiv2026

High-Resolution Multi-Target DOA Estimation for Resonant Beam Systems

Direction of arrival (DOA) estimation technology offers a promising solution to address the sensing and positioning demands of Internet of Things (IoT) devices. Optical resonant beam systems (RBS), owing to their inherent characteristics of self-alignment, self-established energy focusing, and passive target sensing, make them naturally suited for {\color{blue}DOA} estimation in IoT scenarios. However, RBS suffer from limited angular resolution and a narrow field of view (FoV) in multi-target environments. To overcome these limitations, this paper proposes a high-resolution wide-field-of-view resonant beam DOA estimation system (RB-HWDOA). The RB-HWDOA integrates an optical spectrum-based DOA estimation algorithm (OSB-DOA), which leverages amplitude information in the two-dimensional Fourier spectrum of the resonant beam, {\color{blue}overcoming the resolution limit imposed by the beam size in spatial-domain methods}. Furthermore, we designed a {\color{blue}telescope} modulation (TM) structure to correct phase and direction mismatches, enabling a multi-Tx framework that focuses beams onto a common sensing module, thereby extending the effective FoV. Combined with the OSB-DOA algorithm, this design supports high-resolution DOA estimation for {\color{blue}multiple targets simultaneously over a wide FoV}. Simulation results show that OSB-DOA resolves angular separations down to $0.1^{\circ}$ across multiple resonant beams, remains robust under noise, {\color{blue}and the TM architecture enables multi-Tx integration for wide-FoV coverage}, making RB-HWDOA a scalable and efficient solution for passive multi-target DOA estimation in complex IoT environments.

physics.optics↗

arXiv2025

Simultaneous Self-Localization and Base Station Localization with Resonant Beam

High-precision positioning in GPS-denied environments is a demanding but challenging technology. Resonant Beam Positioning (RBP) utilizes a resonant beam with properties such as energy focusing, self-establishment, self-alignment, and passive operation, offering a promising solution for this task. However, traditional RBP algorithms require a fixed number of resonant beam base stations, which can be costly to expand coverage. To address this limitation, we propose a distributed resonant beam positioning (DRBP) system that simultaneously estimates the base station and mobile target (MT) positions. Firstly, the MT receives resonant beam samples to locate the base station in the limited field of view (FoV) region. Subsequently, it estimates self-position based on the known locations of the base stations. During moving, the DRBP system facilitates self-positioning on the MT side, enabling dynamic expansion of both the number of base stations and the coverage area. Numerical results demonstrate that DRBP achieves a positioning root mean square error (RMSE) of $0.1$ m and a rotation RMSE of 2$^\circ$, validating the system's high accuracy.

physics.optics↗

arXiv2024

Planning In Natural Language Improves LLM Search For Code Generation

While scaling training compute has led to remarkable improvements in large language models (LLMs), scaling inference compute has not yet yielded analogous gains. We hypothesize that a core missing component is a lack of diverse LLM outputs, leading to inefficient search due to models repeatedly sampling highly similar, yet incorrect generations. We empirically demonstrate that this lack of diversity can be mitigated by searching over candidate plans for solving a problem in natural language. Based on this insight, we propose PlanSearch, a novel search algorithm which shows strong results across HumanEval+, MBPP+, and LiveCodeBench (a contamination-free benchmark for competitive coding). PlanSearch generates a diverse set of observations about the problem and then uses these observations to construct plans for solving the problem. By searching over plans in natural language rather than directly over code solutions, PlanSearch explores a significantly more diverse range of potential solutions compared to baseline search methods. Using PlanSearch on top of Claude 3.5 Sonnet achieves a state-of-the-art pass@200 of 77.0% on LiveCodeBench, outperforming both the best score achieved without search (pass@1 = 41.4%) and using standard repeated sampling (pass@200 = 60.6%). Finally, we show that, across all models, search algorithms, and benchmarks analyzed, we can accurately predict performance gains due to search as a direct function of the diversity over generated ideas. Code can be found at https://github.com/scaleapi/plansearch.

cs.LG↗

arXiv2024

High-Efficiency Resonant Beam Charging and Communication

With the development of Internet of Things (IoT), demands of power and data for IoT devices increase drastically. In order to resolve the supply-demand contradiction, simultaneous wireless information and power transfer (SWIPT) has been envisioned as an enabling technology by providing high-power energy transfer and high-rate data delivering concurrently. In this paper, we introduce a high-efficiency resonant beam (RB) charging and communication scheme. The scheme utilizes the semiconductor materials as gain medium, which has a better energy absorption capacity compared with the traditional solid-state one. Moreover, the telescope internal modulator (TIM) are adopted in the scheme which can concentrate beams to match the gain size, reducing the transmission loss. To evaluate the scheme SWIPT performance, we establish an analytical model and study the influence factors of its beam transmission, energy conversion, output power, and spectral efficiency. Numerical results shows that the proposed RB system can realize 16 W electric power output with 11 % end-to-end conversion efficiency, and support 18 bit/s/Hz spectral efficiency for communication.

cs.ET↗

arXiv2022

Transmission Model for Resonant Beam SWIPT with Telescope Internal Modulator

To satisfy the long-range and energy self-sustaining communication needs of electronic devices in the Internet of Things (IoT), we introduce a simultaneous wireless information and power transfer (SWIPT) system using the resonant beam that incorporates a telescope modulator inside a cavity for suppressing diffraction losses. We theoretically analyze power transfer in the resonant beam system with telescope internal modulator (TIM-RBS) considering the electromagnetic field propagation, the end-to-end (E2E) power transfer, and power and information reception. The numerical evaluation demonstrates that the TIM can effectively compress the beam spot, which allows the TIM-RBS to transmit energy twice as far as the RBS without TIM at higher power. Additionally, the largest transmission distance and maximum output power are proportional to the input power, and about 34m transmission distance, 4W electric power, and 12bps/Hz spectral efficiency can be achieved in the TIM-RBS with 200W input power. Hence, TIM-RBS can be considered as a promising option for realizing long-range, high-power, and high-rate SWIPT.

eess.SY↗

arXiv2022

Long-Range Optical Wireless Information and Power Transfer

Simultaneous wireless information and power transfer (SWIPT) is a remarkable technology to support both the data and the energy transfer in the era of Internet of Things (IoT). In this paper, we proposed a long-range optical wireless information and power transfer system utilizing retro-reflectors, a gain medium, a telescope internal modulator to form the resonant beam, achieving high-power and high-rate SWIPT. We adopt the transfer matrix, which can depict the beam modulated, resonator stability, transmission loss, and beam distribution. Then, we provide a model for energy harvesting and data receiving, which can evaluate the SWIPT performance. Numerical results illustrate that the proposed system can simultaneously supply 0$\sim$9 W electrical power and 18 bit/s/Hz spectral efficiency over 20 m distance.

cs.ET↗

arXiv2022

Charging A Smartphone Over the Air: The Resonant Beam Charging Method

Wireless charging for mobile Internet of Things (IoT) devices such as smartphones is extremely difficult. To reduce energy dissipation during wireless transmission in mobile scenarios, laser or narrow radio beams with sophisticated tracking control are typically required. However, reaching the necessary tracking accuracy and reliability is really difficult. In this paper, inspired by the features of optical resonators and retroreflectors, we develop an experiment on a self-aligned resonant beam charging system for long-distance mobile power transfer. It exploits light resonances inside a double-retroreflector-based spatially separated laser resonator (SSLR), which eliminates the requirement for any kind of tracking control. Focal telecentric cat's eye retroreflectors are employed here. The SSLR was investigated by both theoretical calculation and experiment. We also well assembled the transmitter and the receiver and demonstrated its application in mobile smartphone charging. The results show that above 5-W optical power (also obtained more than 0.6-W electrical power) transferring with negligible diffraction loss to a few-centimeter-size receiver is realized while the receiver moves arbitrarily within 2-m vertical distance and 6° field of view from the transmitter. The maximum horizontal moving range is up to 18cm. This wireless charging system empowers a smartphone in mobile operation with unlimited battery life without the need for a cable.

eess.SP↗