arXiv subjects

Yanxiao Zhao

Publications and source records attributed to Yanxiao Zhao.

14 recordsLinked to original sources

arXiv2026

BR-FiLM: Bounded Residual Channel-Quality Conditioning for Automatic Modulation Recognition

Automatic Modulation Recognition (AMR) plays a crucial role in enabling robust, adaptive, and secure communication for military and civilian applications. Deep learning has enabled effective AMR methods that overcome the computational inefficiency of traditional approaches. However, these deep learning based methods often degrade significantly in low SNR conditions, where noise obscures modulation-discriminative waveform features. In this paper, we propose Bounded Residual Feature-wise Linear Modulation (BR-FiLM), a channel-quality conditioning block for AMR, which can be inserted into AMR classifiers with intermediate feature representations. We construct BR-FiLMNet by inserting the proposed BR-FiLM block into a Multi-Channel Convolutional Long Short-Term Deep Neural Network (MCLDNN) backbone. BR-FiLMNet conditions convolutional, recurrent, and dense features through gated residual corrections while preserving the original I/Q-driven feature path. Experimental results on RadioML 2016.10a show that BR-FiLMNet improves mean accuracy from 61.79% to 67.74% and low-SNR accuracy (SNR <= 0 dB) from 37.12% to 46.44% compared to MCLDNN. We further evaluate BR-FiLMNet against recent transformer-style baselines. The results indicate that BR-FiLMNet delivers significant and reliable performance gains, as validated through paired statistical testing.

eess.SP↗

arXiv2026

SATQuest: A Verifier for Logical Reasoning Evaluation and Reinforcement Fine-Tuning of LLMs

Large language models (LLMs) exhibit strong general reasoning, yet the community lacks controllable, scalable, and verifiable tools to analyze and improve these abilities. We present SATQuest, a verifier that generates diverse SAT-based reasoning tasks directly from Conjunctive Normal Form (CNF) instances and checks answers objectively with PySAT. SATQuest factorizes evaluation along three orthogonal dimensions: instance, problem type, and question format, enabling fine-grained, multi-dimensional analysis and reinforcement fine-tuning. Randomized CNF generation mitigates memorization and supports reproducible experiments. Using SATQuest, we benchmark a range of open- and closed-weight LLMs and uncover persistent gaps in logical reasoning, particularly on higher-complexity tasks and in transfer beyond familiar mathematical notation to machine or narrative formats. We further show that reinforcement fine-tuning with SATQuest rewards substantially boosts targeted performance and generalizes to larger instances, while cross-format robustness remains challenging. Collectively, SATQuest provides verifier-backed infrastructure for controlled, scalable, and reproducible empirical research on LLM logical reasoning and its training.

cs.AI↗

arXiv2026

SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL

Computer use agents (CUAs) are emerging as a powerful interface for automating complex digital workflows through visual perception and GUI execution. Online reinforcement learning with verifiable rewards (RLVR) has emerged as a key direction for scaling their capabilities. However, this paradigm is bottlenecked by verifiable data scarcity and online RL inefficiency. To break these barriers, we introduce ScaleCUA, a unified framework that scales online RL for CUAs via verifiable task synthesis and efficient training. At the data level, we design VeriGen, an end-to-end framework for generating verifiable RL tasks through iterative docker interactions and a multi-agent feedback loop. Scaled to 100+ concurrent agent workers via a shared docker interaction probe, this pipeline produces 24K+ verifiable tasks and nearly 3K high-quality RL tasks. To maximize sample efficiency, we propose Frontier Sampling, which tracks per-task capability and allocates rollouts to the current learning frontier. On the training side, we further design Visual Context Segmentation, a sliding window over recent visual context that balances rollout and training-engine pressure, yielding a 2.83x training speedup over step-wise decomposition. Together, ScaleCUA achieves 68.7% on OSWorld and 54.0% on ScienceBoard, establishing new state-of-the-art performance among open-source computer use agents. Code, models, and datasets are available at https://github.com/THUDM/SCALE-CUA.

cs.AI↗

arXiv2026

Forget to Improve: On-Device LLM-Agent Continual Learning via Budget-Curated Memory

On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights. This memory is hard-bounded and exposed: it consumes RAM and energy, reaches peers through a thin uplink, and becomes an attack surface because it is writable by what the agent reads. Existing systems each cover one part of this problem: agentic memories grow without a budget, on-device methods keep entries by success alone, and poisoning is studied mainly as an attack rather than as a memory-governance problem. We propose \sys{}, a single net-value-per-byte score that governs an agent's experience-memory lifecycle. The main idea is to let the budget act as the curator: each entry is scored as value minus harm, per byte, so one ruler decides what to keep, share, and trust. \sys{} makes three decisions: (1) \textbf{KEEP} evicts low-value bytes under the RAM and energy budget; (2) \textbf{SHARE} sends an insight only when its value exceeds its uplink cost; and (3) \textbf{TRUST} gates a peer entry by provenance. On language-model-agent task-drift benchmarks and a real heterogeneous Jetson testbed with two robot-arm nodes and a hub, \sys{} reduces memory by $2.7\times$ and uplink by $2.4\times$, drives injection success from 0.75 to zero, and raises accuracy on cases corrupted by poison or stale memory. Curating by net value reduces footprint, energy, uplink, and injection success together without reducing accuracy. In this setting, forgetting by net value improves the agent rather than weakening it.

cs.LG↗

arXiv2026

GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

We present GLM-5V-Turbo, a step toward native foundation models for multimodal agents. As foundation models are increasingly deployed in real environments, agentic capability depends not only on language reasoning, but also on the ability to perceive, interpret, and act over heterogeneous contexts such as images, videos, webpages, documents, GUIs. GLM-5V-Turbo is built around this objective: multimodal perception is integrated as a core component of reasoning, planning, tool use, and execution, rather than as an auxiliary interface to a language model. This report summarizes the main improvements behind GLM-5V-Turbo across model design, multimodal training, reinforcement learning, toolchain expansion, and integration with agent frameworks. These developments lead to strong performance in multimodal coding, visual tool use, and framework-based agentic tasks, while preserving competitive text-only coding capability. More importantly, our development process offers practical insights for building multimodal agents, highlighting the central role of multimodal perception, hierarchical optimization, and reliable end-to-end verification.

cs.CV↗

arXiv2026

Learning to Edit Knowledge via Instruction-based Chain-of-Thought Prompting

Large language models (LLMs) can effectively handle outdated information through knowledge editing. However, current approaches face two key limitations: (I) Poor generalization: Most approaches rigidly inject new knowledge without ensuring that the model can use it effectively to solve practical problems. (II) Narrow scope: Current methods focus primarily on structured fact triples, overlooking the diverse unstructured forms of factual information (e.g., news, articles) prevalent in real-world contexts. To address these challenges, we propose a new paradigm: teaching LLMs to edit knowledge via Chain of Thoughts (CoTs) reasoning (CoT2Edit). We first leverage language model agents for both structured and unstructured edited data to generate CoTs, building high-quality instruction data. The model is then trained to reason over edited knowledge through supervised fine-tuning (SFT) and Group Relative Policy Optimization (GRPO). At inference time, we integrate Retrieval-Augmented Generation (RAG) to dynamically retrieve relevant edited facts for real-time knowledge editing. Experimental results demonstrate that our method achieves strong generalization across six diverse knowledge editing scenarios with just a single round of training on three open-source language models. The codes are available at https://github.com/FredJDean/CoT2Edit.

cs.CL↗

arXiv2025

ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use Agents

We introduce ComputerRL, a framework for autonomous desktop intelligence that enables agents to operate complex digital workspaces skillfully. ComputerRL features the API-GUI paradigm, which unifies programmatic API calls and direct GUI interaction to address the inherent mismatch between machine agents and human-centric desktop environments. Scaling end-to-end RL training is crucial for improvement and generalization across diverse desktop tasks; however, it remains challenging due to environmental inefficiency and instability during extended training. To support scalable and robust training, we develop a distributed RL infrastructure capable of orchestrating thousands of parallel virtual desktop environments to accelerate large-scale online RL. Furthermore, we propose Entropulse, a training strategy that alternates reinforcement learning with supervised fine-tuning, effectively mitigating entropy collapse during extended training runs. We employ ComputerRL on open models GLM-4-9B-0414 and GLM-4.1V-9B-Thinking, and evaluate them on the OSWorld benchmark. The AutoGLM-OS-9B achieves a new state-of-the-art accuracy of 48.9%, demonstrating significant improvements for general agents in desktop automation. Our code and the new OfficeWorld benchmark are available at https://github.com/thudm/ComputerRL. The algorithm and framework are adopted in building AutoGLM (Liu et al., 2024b).

cs.AI↗

arXiv2025

A Multimodal Cross-View Model for Predicting Postoperative Neck Pain in Cervical Spondylosis Patients

Neck pain is the primary symptom of cervical spondylosis, yet its underlying mechanisms remain unclear, leading to uncertain treatment outcomes. To address the challenges of multimodal feature fusion caused by imaging differences and spatial mismatches, this paper proposes an Adaptive Bidirectional Pyramid Difference Convolution (ABPDC) module that facilitates multimodal integration by exploiting the advantages of difference convolution in texture extraction and grayscale invariance, and a Feature Pyramid Registration Auxiliary Network (FPRAN) to mitigate structural misalignment. Experiments on the MMCSD dataset demonstrate that the proposed model achieves superior prediction accuracy of postoperative neck pain recovery compared with existing methods, and ablation studies further confirm its effectiveness.

cs.CV↗

arXiv2025

CAMEL: Continuous Action Masking Enabled by Large Language Models for Reinforcement Learning

Reinforcement learning (RL) in continuous action spaces encounters persistent challenges, such as inefficient exploration and convergence to suboptimal solutions. To address these limitations, we propose CAMEL, a novel framework integrating LLM-generated suboptimal policies into the RL training pipeline. CAMEL leverages dynamic action masking and an adaptive epsilon-masking mechanism to guide exploration during early training stages while gradually enabling agents to optimize policies independently. At the core of CAMEL lies the integration of Python-executable suboptimal policies generated by LLMs based on environment descriptions and task objectives. Although simplistic and hard-coded, these policies offer valuable initial guidance for RL agents. To effectively utilize these priors, CAMEL employs masking-aware optimization to dynamically constrain the action space based on LLM outputs. Additionally, epsilon-masking gradually reduces reliance on LLM-generated guidance, enabling agents to transition from constrained exploration to autonomous policy refinement. Experimental validation on Gymnasium MuJoCo environments demonstrates the effectiveness of CAMEL. In Hopper-v4 and Ant-v4, LLM-generated policies significantly improve sample efficiency, achieving performance comparable to or surpassing expert masking baselines. For Walker2d-v4, where LLMs struggle to accurately model bipedal gait dynamics, CAMEL maintains robust RL performance without notable degradation, highlighting the framework's adaptability across diverse tasks. While CAMEL shows promise in enhancing sample efficiency and mitigating convergence challenges, these issues remain open for further research. Future work aims to generalize CAMEL to multimodal LLMs for broader observation-action spaces and automate policy evaluation, reducing human intervention and enhancing scalability in RL training pipelines.

cs.LG↗

arXiv2024

Snapshot Reinforcement Learning: Leveraging Prior Trajectories for Efficiency

Deep reinforcement learning (DRL) algorithms require substantial samples and computational resources to achieve higher performance, which restricts their practical application and poses challenges for further development. Given the constraint of limited resources, it is essential to leverage existing computational work (e.g., learned policies, samples) to enhance sample efficiency and reduce the computational resource consumption of DRL algorithms. Previous works to leverage existing computational work require intrusive modifications to existing algorithms and models, designed specifically for specific algorithms, lacking flexibility and universality. In this paper, we present the Snapshot Reinforcement Learning (SnapshotRL) framework, which enhances sample efficiency by simply altering environments, without making any modifications to algorithms and models. By allowing student agents to choose states in teacher trajectories as the initial state to sample, SnapshotRL can effectively utilize teacher trajectories to assist student agents in training, allowing student agents to explore a larger state space at the early training phase. We propose a simple and effective SnapshotRL baseline algorithm, S3RL, which integrates well with existing DRL algorithms. Our experiments demonstrate that integrating S3RL with TD3, SAC, and PPO algorithms on the MuJoCo benchmark significantly improves sample efficiency and average return, without extra samples and additional computational resources.

cs.LG↗

arXiv2024

Open RL Benchmark: Comprehensive Tracked Experiments for Reinforcement Learning

In many Reinforcement Learning (RL) papers, learning curves are useful indicators to measure the effectiveness of RL algorithms. However, the complete raw data of the learning curves are rarely available. As a result, it is usually necessary to reproduce the experiments from scratch, which can be time-consuming and error-prone. We present Open RL Benchmark, a set of fully tracked RL experiments, including not only the usual data such as episodic return, but also all algorithm-specific and system metrics. Open RL Benchmark is community-driven: anyone can download, use, and contribute to the data. At the time of writing, more than 25,000 runs have been tracked, for a cumulative duration of more than 8 years. Open RL Benchmark covers a wide range of RL libraries and reference implementations. Special care is taken to ensure that each experiment is precisely reproducible by providing not only the full parameters, but also the versions of the dependencies used to generate it. In addition, Open RL Benchmark comes with a command-line interface (CLI) for easy fetching and generating figures to present the results. In this document, we include two case studies to demonstrate the usefulness of Open RL Benchmark in practice. To the best of our knowledge, Open RL Benchmark is the first RL benchmark of its kind, and the authors hope that it will improve and facilitate the work of researchers in the field.

cs.LG↗

arXiv2018

RF Energy Harvesting Sensor Networks for Healthcare of Animals: Opportunities and Challenges

In recent years, the radio frequency (RF) energy harvesting technique is considered as a favorable alternative to supply power for the next-generation wireless sensor networks. Due to the features of energy self-sustainability and long lifetime, the energy harvesting sensor network (RF-EHSN) becomes a promising solution to provide smart healthcare services. Nowadays, many energy harvesting based applications have been developed for monitoring the health status of human beings; how to benefit animals, however, has not yet drawn people's attention. This article explores the potential of applying RF-EHSNs to monitoring the health level of animals. The unique challenges and potential solutions at different layers of an RF-EHSN for animals' healthcare service are studied.

cs.NI↗

arXiv2018

DTER: Schedule Optimal RF Energy Request and Harvest for Internet of Things

We propose a new energy harvesting strategy that uses a dedicated energy source (ES) to optimally replenish energy for radio frequency (RF) energy harvesting powered Internet of Things. Specifically, we develop a two-step dual tunnel energy requesting (DTER) strategy that minimizes the energy consumption on both the energy harvesting device and the ES. Besides the causality and capacity constraints that are investigated in the existing approaches, DTER also takes into account the overhead issue and the nonlinear charge characteristics of an energy storage component to make the proposed strategy practical. Both offline and online scenarios are considered in the second step of DTER. To solve the nonlinear optimization problem of the offline scenario, we convert the design of offline optimal energy requesting problem into a classic shortest path problem and thus a global optimal solution can be obtained through dynamic programming (DP) algorithms. The online suboptimal transmission strategy is developed as well. Simulation study verifies that the online strategy can achieve almost the same energy efficiency as the global optimal solution in the long term.

eess.SP↗

arXiv2018

Revisiting Transmission Scheduling in RF Energy Harvesting Wireless Communications

The transmission scheduling is a critical problem in radio frequency (RF) energy harvesting communications. Existing transmission strategies in an RF-based energy harvesting system is mainly based on a classic model, in which the data transmission is scheduled in a fixed feasible energy tunnel. In this paper, we re-examine the classic energy harvesting model and show through the theoretical analysis and experimental results that the bounds of feasible energy tunnel are dynamic, which can be affected by the transmission scheduling due to the impact of residual energy on the harvested one. To describe a practical energy harvesting process more accurately, a new model is proposed by adding a feedback loop that reflects the interplay between the energy harvest and the data transmission. Furthermore, to improve network performance, we revisit the design of an optimal transmission scheduling strategy based on the new model. To handle the challenge of the endless feedback loop in the new model, a recursive algorithm is developed. The simulation results reveal that the new transmission scheduling strategy can balance the efficiency of energy reception and energy utilization regardless of the length of energy packets, achieving improved throughput performance for wireless communications.

eess.SP↗