Searcharxiv⌕ Search

arXiv subjects

Xiaopeng Yuan

Publications and source records attributed to Xiaopeng Yuan.

At least 19 recordsLinked to original sources
arXiv2026

AoI-Oriented Globally Optimal Joint Source and Update Scheduling in Fluid Antenna Systems

As a promising technique, fluid antennas enable adaptive radio environment management and interference mitigation through reconfigurable fluid port selections. In this work, to explore the benefits of fluid antennas for data freshness enhancement, we consider a fluid-antenna assisted status update system supported by multiple source nodes monitoring the same environmental status. We assume a subset of the source nodes are activated to report status updates with different periods. Each user is assigned to one source node and equipped with an fluid antenna to adaptively enhance the channel gain to assigned source node while mitigating interference from other activated source nodes. With maximal signal-to-interference-noise ratio (SINR)-based fluid port selection at all users, we formulate an optimization problem to minimize the maximum average age of information (AoI), where source node activation and assignment, i.e., source scheduling, is jointly optimized with the update periods of all activated source nodes. To optimally solve the resulting mixed-integer nonlinear problem, we first consider given source scheduling decision and apply performance achievability analysis. Aided by fixpoint theory, we propose an efficient bisection algorithm for optimal update scheduling. Based on these characterizations, we further propose a filtering algorithm which efficiently eliminates all non-optimal source scheduling decisions. The globally optimal joint solution is then obtained by combining the resulting optimal source scheduling with its corresponding optimal update scheduling. Numerical results validate the optimality of proposed solution and demonstrate the effectiveness of fluid antennas in enhancing data freshness.

eess.SY↗
arXiv2026

Beyond Asking: A Pipeline for Personalized Game Generation that Reads Players from Behavior

Personalized game generation requires inferring a player's abilities and behavioral style from how they play. Large language models have made this inference more attainable than ever: an LLM can read a raw gameplay transcript and produce a fluent, plausible profile of the player. Plausible, however, is not verified, and verification is precisely what the field lacks: latent traits are unobservable; questionnaires provide noisy proxies and become circular when self-reports are used to validate behavior-based inference; and behavior itself is ambiguous without context -- a player who never collects an item may not want it, or may never have had the chance. We address both problems. First, we construct a synthetic player population whose traits are ground truth by construction: each trait is an explicit bot parameter, accepted only after controlled manipulation produces consistent, trait-specific behavioral change. Unlike prior parameter-recovery work that inverts a known decision model, our benchmark evaluates policy-agnostic inference from behavioral transcripts alone. Second, we introduce an opportunity-aware decision-moment representation that disentangles preference from the chance to express it; ablating it selectively degrades opportunity-dependent traits. On this benchmark, few-shot LLM inference outperforms embedding- and rule-based baselines on most traits, though feature-based supervised regressors remain stronger overall. Finally, we close the loop: inferred profiles drive difficulty adaptation, evaluated against ground-truth references and mismatched-profile controls, and an exploratory human study examines whether these findings transfer to real players.

cs.AI↗
arXiv2026

KV-PRM: Efficient Process Reward Modeling via KV-Cache Transfer for Multi-Agent Test-Time Scaling

Process Reward Models (PRMs) have been proven to be highly effective in guiding test-time scaling (TTS) methods, which significantly boost the capabilities of LLM-based multi-agent systems. However, existing PRMs are text-based: they re-encode the entire trajectory text from scratch. In long multi-agent rollouts, the scoring cost, growing quadratically with respect to sequence length L, creates a severe computational bottleneck, severely limiting PRMs' application in long-context scenarios. To resolve this, we introduce KV-PRM, a highly efficient process reward model that eliminates the heavy text re-encoding by directly reading the KV cache produced naturally during the LLM's generation phase. By processing a single "verify token" against the pre-existing KV cache, KV-PRM reduces the scoring cost from O(L^2) to O(L). We formally prove that the KV cache contains strictly greater information capacity than text, and is more efficient for downstream reward modeling. Empirically, across the MATH, GSM8K, and AIME benchmarks, KV-PRM matches or strictly outperforms text-PRMs under various TTS methods such as Beam Search, MCTS, and Weighted Voting, with up to a 5,000x reduction in scoring FLOPs, a 37x reduction in latency, and a 34x reduction in per-sequence memory footprint compared to text-based PRMs.

cs.AI↗
arXiv2026

Minimizing Quantized Semantic Age of Information (QSAoI) in Foundation Model-Based Semantic Communications

The emerging techniques of semantic communications and edge computing in 6G networks necessitate a paradigm shift toward co-designed semantic-aware and adaptive resource allocation for short-packet transmissions. However, there is a fundamental gap between the semantic layer and the physical layer under low-latency finite blocklength (FBL) effects. To bridge this gap, we introduce the Quantized Semantic Age of Information (QSAoI), a novel metric that rigorously captures the trade-offs among freshness and semantic efficiency of high-level features in real-time communication in the FBL regime. Guided by this metric, we propose a novel foundation model-based efficient co-designed framework to minimize the expected QSAoI over wireless fading channels in latency-constrained semantic communication. Specifically, we formulate a non-linear joint optimization problem to dynamically optimize the block-wise mixed-precision quantization (MPQ) strategy and the physical blocklength. To efficiently resolve this complex problem, we develop a high-efficiency low-complexity algorithm based on fixpoint inspection and bisection search. Extensive simulations validate that our proposed algorithm dynamically adapts the semantic quantization precision to varying channel conditions, effectively minimizing the expected QSAoI compared to baselines.

eess.SP↗
arXiv2026

EASE-TTT: Evidence-Aligned Selective Test-Time Training for Long-Context Question Answering

Long-context question answering (QA) remains challenging for smaller language models even when answer-bearing evidence is already present in the input. Existing within-context retrieval methods localize and expose candidate evidence chunks for the question, but they stop at input-level evidence exposure rather than adapting the query-side attention parameters that control how the model allocates attention over full-context positions. In contrast, lightweight test-time adaptation methods, such as query-only test-time training (qTTT), leave evidence localization unresolved because their generic span-level self-supervised objectives do not identify which context positions support the current answer. In this paper, we propose Evidence-Aligned SElective Test-Time Training (EASE-TTT), a within-context retrieval-augmented test-time training framework that converts selected evidence chunks into a soft attention supervision target over their token positions. Instead of replacing the full context with retrieved chunks, EASE-TTT uses the resulting attention target to guide query-side adaptation, with the adapted model generating the final answer from the original full context. Experiments on six LongBench QA tasks and three small decoder-only language models show that EASE-TTT achieves the strongest macro-average performance among full-context inference, retrieval-only baselines, and qTTT, supporting evidence-aligned test-time adaptation in long-context QA.

cs.CL↗
arXiv2026

Closing the Loop on Latent Reasoning via Test-Time Reconstruction

Recent work moves intermediate reasoning from natural-language traces into latent or cache-level representations to reduce token overhead and avoid a discrete communication bottleneck. However, this shift also removes a key advantage of textual reasoning: intermediate states are no longer inspectable, making it difficult to determine whether a latent state still preserves the constraints of the original query. As a result, latent reasoning typically operates in an open loop, where a latent state is produced and consumed without an input-anchored fidelity check. We propose ReLAT (Reconstruction-Guided Latent Reasoning At Test Time), a self-supervised test-time training method that closes this loop using the query itself as the reference. Our key observation is that if a latent state faithfully represents a query, the query should be recoverable from it; if the query cannot be recovered, the latent state has lost task-relevant information. ReLAT operationalizes this principle by constructing a differentiable Question -> Latent Thought -> Question cycle and optimizing query reconstruction loss through the latent thought before answer generation. This anchors opaque latent computation to the problem specification it is supposed to represent. Across mathematical reasoning, knowledge QA, and code generation benchmarks on the Qwen family, ReLAT consistently improves over single-model inference, text-based collaboration, open-loop latent collaboration, and alternative test-time training objectives. On Qwen3-8B, ReLAT raises AIME 2024 accuracy from 56.7% to 73.3%, a 16.6-point gain over the strongest open-loop latent baseline.

cs.AI↗
arXiv2026

Agent Primitives: Reusable Latent Building Blocks for Multi-Agent Systems

While existing multi-agent systems (MAS) can handle complex problems by enabling collaboration among multiple agents, they are often highly task-specific, relying on manually crafted agent roles and interaction prompts, which leads to increased architectural complexity and limited reusability across tasks. Moreover, most MAS communicate primarily through natural language, making them vulnerable to error accumulation and instability in long-context, multi-stage interactions within internal agent histories. In this work, we propose \textbf{Agent Primitives}, a set of reusable latent building blocks for LLM-based MAS. Inspired by neural network design, where complex models are built from reusable components, we observe that many existing MAS architectures can be decomposed into a small number of recurring internal computation patterns. Based on this observation, we instantiate three primitives: Review, Voting and Selection, and Planning and Execution. All primitives communicate internally via key-value (KV) cache, which improves both robustness and efficiency by mitigating information degradation across multi-stage interactions. To enable automatic system construction, an Organizer agent selects and composes primitives for each query, guided by a lightweight knowledge pool of previously successful configurations, forming a primitive-based MAS. Experiments show that primitives-based MAS improve average accuracy by 12.0-16.5\% over single-agent baselines, reduce token usage and inference latency by approximately 3$\times$-4$\times$ compared to text-based MAS, while incurring only 1.3$\times$-1.6$\times$ overhead relative to single-agent inference and providing more stable performance across model backbones.

cs.MA↗
arXiv2026

Do Self-Evolving Agents Forget? Capability Degradation and Preservation in Lifelong LLM Agent Adaptation

Recent advances in LLM agents enable systems that autonomously refine workflows, accumulate reusable skills, self-train their underlying models, and maintain persistent memory. However, we show that such self-evolution is often non-monotonic: adapting to new task distributions can progressively degrade previously acquired capabilities across all major evolution channels. We identify this phenomenon as \emph{capability erosion under self-evolution} and show that it consistently emerges across workflow, skill, model, and memory evolution. To mitigate this issue, we propose \emph{Capability-Preserving Evolution} (CPE), a general stabilization principle that constrains destructive capability drift during continual adaptation. Across all four evolution dimensions, CPE consistently improves retained capability stability while preserving adaptation performance. For example, in workflow evolution, CPE improves retained simple-task performance from 41.8\% to 52.8\% under GPT-5.1 optimization while simultaneously achieving stronger complex-task adaptation. Our findings suggest that stable long-horizon self-evolving agents require not only acquiring new capabilities, but also explicitly preserving previously learned ones during continual adaptation.

cs.AI↗
arXiv2026

Analytically Characterized Optimal Power Control for Signal-Level-Integrated Sensing, Computing and Communication in Federated Learning

In the Internet-of-Things (IoT) era, efficient functionality integration is essential to address the growing demands of communication, computation, and sensing. Signal-level integrated sensing, computing, and communication (Sig-ISCC) is envisioned, where a single waveform simultaneously supports sensing, computing and communication via over-the-air computation (AirComp). Meanwhile, federated learning (FL) is widely regarded as a promising distributed machine learning framework that enables network intelligence in a privacy-preserving and secure manner, and exhibits strong synergy with AirComp, which alleviates the communication bottleneck of FL. In this paper, we study uplink Sig-ISCC design for AirComp-FL with joint target detection. We formulate the joint power and receive-scaling control problem, where edge devices' transmitted signals should serve both sensing and AirComp purposes. The goal is to minimize the AirComp aggregation distortion subject to a joint target-detection requirement. Although the resulting problem is non-convex in the original variables, we show that it admits an equivalent convex reformulation after a suitable variable transformation. By exploiting analytical optimality properties, we develop a robust, optimal, and polynomial-time-complexity algorithm that efficiently achieves the optimal transmit powers and receive scaling factor. Simulation results validate the optimality and numerical robustness of the proposed algorithm and show its superior FL performance compared to baseline methods.

cs.IT↗
arXiv2026

Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems

Multi-agent systems built on large language models have shown strong performance on complex reasoning tasks, yet most work focuses on agent roles and orchestration while treating inter-agent communication as a fixed interface. Latent communication through internal representations such as key-value caches offers a promising alternative to text-based protocols, but existing approaches do not jointly optimize communication with multi-agent reasoning. Therefore we propose DiffMAS, a training framework that treats latent communication as a learnable component of multi-agent systems. DiffMAS performs parameter-efficient supervised training over multi-agent latent trajectories, enabling agents to jointly learn how information should be encoded and interpreted across interactions. Experiments on mathematical reasoning, scientific QA, code generation, and commonsense benchmarks show that DiffMAS consistently improves reasoning accuracy and decoding stability over single-agent inference, text-based multi-agent systems, and prior latent communication methods, achieving 26.7% on AIME24, 20.2% on GPQA-Diamond, and consistent gains across reasoning benchmarks.

cs.AI↗
arXiv2026

Efficient Joint Resource Allocation for Wireless Powered ISAC with Target Localization

Wireless powered integrated sensing and communication (ISAC) faces a fundamental tradeoff between energy supply, communication throughput, and sensing accuracy. This paper investigates a wireless powered ISAC system with target localization requirements, where users harvest energy from wireless power transfer (WPT) and then conduct ISAC transmissions in a time-division manner. In addition to energy supply, the WPT signal also contributes to target sensing, and the localization accuracy is characterized by Cramér-Rao bound (CRB) constraints. Under this setting, we formulate a max-min throughput maximization problem by jointly allocating the WPT duration, ISAC transmission time allocation, and transmit power. Due to the nonconvexity of the resulting problem, a suitable reformulation is developed by exploiting variable substitutions and the monotonicity of logarithmic functions, based on which an efficient successive convex approximation (SCA)-based iterative algorithm is proposed. Simulation results demonstrate convergence and significant performance gains over benchmark schemes, highlighting the importance of coordinated time-power optimization in balancing sensing accuracy and communication performance in wireless powered ISAC systems.

eess.SP↗
arXiv2026

Efficient Trajectory Design and Communication Scheduling for Dual-UAV Jamming-Aided Secure Communication Networks

We study dual-unmanned aerial vehicle (UAV) jamming-aided secure communication networks, in which one UAV delivers confidential data to multiple ground users (GUs), while a cooperative UAV provides protective interference against a ground eavesdropper. To enforce fairness, we maximize the minimum secrecy throughput across GUs by jointly designing trajectories and communication scheduling. The key difficulty lies in the continuous-time nature of UAV trajectories and the tight space-time coupling between the transmitter and the jammer, which jointly render the problem infinite-dimensional and nonconvex. To address these challenges, we characterize, for the first time, the structure of the optimal trajectories and rigorously prove that they follow a collaborative successive hover-and-fly (co-SHF) structure, where the two UAVs visit a limited number of synchronized co-hovering point pairs, and during each flight segment at least one UAV moves at maximum speed. Leveraging this structure, we reformulate the problem into a finite-dimensional form, without loss of optimality, over hovering and turning points, hovering durations, and scheduling. For tractability, we adopt a minimum-distance approximation of continuous anti-collision constraints and employ concave lower bounds on secrecy throughput within a successive convex approximation (SCA) method, which converges and, thanks to the co-SHF reduction in optimization variables and constraints, achieves low computational complexity. Numerical results show that, compared with time-discretization and no-jamming benchmarks, the proposed co-SHF design improves the min-secrecy and user fairness while requiring significantly less runtime.

eess.SY↗
arXiv2025

UAV-Enabled ISAC: Towards On-Demand Sensing Services and Enhanced Communication

In this paper, we investigate an integrated sensing-and-communication (ISAC) network enabled by an unmanned aerial vehicle (UAV). The UAV is supposed to fly along a periodical circular trajectory at a fixed height for ISAC service supply from the sky. We consider on-demand sensing services, where on-demand detection and on-demand localization requests may be activated at any time toward any position within the targeted serving region. While guaranteeing satisfactory accuracy for both on-demand sensing tasks, we aim at maximizing the minimum achievable throughput among all communication users, via joint optimizing the UAV trajectory and communication user scheduling. To address the complicated problem with infinite sensing constraints, we characterize the on-demand detection constraint as a restricted deployment area for UAV and the on-demand localization constraint as Cramer-Rao Bound (CRB) constraints over finite reference target points, based on which the original problem is simplified to more tractable one. Afterwards, particularly aiming to ensure no violations of CRB constraints, we propose a convex approximation for the reformulated problem, where tight approximation is guaranteed at given local solution. The construction strategy for convex problem approximation allows an efficient iterative algorithm with verified convergence to a superior suboptimal solution. At last, with simulations, we verified the applicability of our developed optimization scheme in strictly fulfilling the on-demand sensing constraints and the effectiveness of our proposed solution for simultaneously enhancing the communication throughput in UAV-enabled ISAC.

eess.SY↗
arXiv2025

Tracing LLM Reasoning Processes with Strategic Games: A Framework for Planning, Revision, and Resource-Constrained Decision Making

Large language models (LLMs) are increasingly used for tasks that require complex reasoning. Most benchmarks focus on final outcomes but overlook the intermediate reasoning steps - such as planning, revision, and decision making under resource constraints. We argue that measuring these internal processes is essential for understanding model behavior and improving reliability. We propose using strategic games as a natural evaluation environment: closed, rule-based systems with clear states, limited resources, and automatic feedback. We introduce a framework that evaluates LLMs along three core dimensions: planning, revision, and resource-constrained decision making. To operationalize this, we define metrics beyond win rate, including overcorrection risk rate, correction success rate, improvement slope, and over-budget ratio. In 4320 adversarial rounds across 12 leading models, ChatGPT-o3-mini achieves the top composite score, with a win rate of 74.7 percent, a correction success rate of 78.6 percent, and an improvement slope of 0.041. By contrast, Qwen-Plus, despite an overcorrection risk rate of 81.6 percent, wins only 25.6 percent of its matches - primarily due to excessive resource use. We also observe a negative correlation between overcorrection risk rate and correction success rate (Pearson r = -0.51, p = 0.093), suggesting that more frequent edits do not always improve outcomes. Our findings highlight the value of assessing not only what LLMs decide but how they arrive at those decisions

cs.AI↗
arXiv2024

Fairness-aware Age-of-Information Minimization in WPT-Assisted Short-Packet Data Collection for mURLLC

The technological landscape is rapidly evolving toward large-scale systems. Networks supporting massive connectivity through numerous Internet of Things (IoT) devices are at the forefront of this advancement. In this paper, we examine Wireless Power Transfer (WPT)-enabled networks, where a server requires to collect data from these IoT devices to compute a task with massive Ultra-Reliable and Low-Latency Communication (mURLLC) services.} We focus on information freshness, using Age-of-Information (AoI) as the key performance metric. Specifically, we aim to minimize the maximum AoI among IoT devices by optimizing the scheduling policy. Our analytical findings demonstrate the convexity of the problem, enabling efficient solutions. We introduce the concept of AoI-oriented cluster capacity and analyze the relationship between the number of supported devices and network AoI performance. Numerical simulations validate our proposed approach's effectiveness in enhancing AoI performance, highlighting its potential for guiding the design of future IoT systems requiring mURLLC services.

cs.IT↗
arXiv2023

Trade Reliability for Security: Leakage-Failure Probability Minimization for Machine-Type Communications in URLLC

How to provide information security while fulfilling ultra reliability and low-latency requirements is one of the major concerns for enabling the next generation of ultra-reliable and low-latency communications service (xURLLC), specially in machine-type communications. In this work, we investigate the reliability-security tradeoff via defining the leakage-failure probability, which is a metric that jointly characterizes both reliability and security performances for short-packet transmissions. We discover that the system performance can be enhanced by counter-intuitively allocating fewer resources for the transmission with finite blocklength (FBL) codes. In order to solve the corresponding optimization problem for the joint resource allocation, we propose an optimization framework, that leverages lower-bounded approximations for the decoding error probability in the FBL regime. We characterize the convexity of the reformulated problem and establish an efficient iterative searching method, the convergence of which is guaranteed. To show the extendability of the framework, we further discuss the blocklength allocation schemes with practical requirements of reliable-secure performance, as well as the transmissions with the statistical channel state information (CSI). Numerical results verify the accuracy of the proposed approach and demonstrate the reliability-security tradeoff under various setups.

cs.IT↗
arXiv2023

Wireless Powered Short Packet Communications with Multiple WPT Sources

We study a multi-source wireless power transfer (WPT) enabled network supporting multi-sensor transmissions. Activated by energy harvesting (EH) from multiple WPT sources, sensors transmit short packets to a destination with finite blocklength (FBL) codes. This work for the first time characterizes the FBL reliability for such multi-source WPT enabled network and provides reliability-oriented resource allocation designs, while a practical nonlinear EH model is considered. For scenario with a fixed frame structure, we maximize the FBL reliability via optimally allocating the transmit power among multi-source. In particular, we first investigate the relationship between the FBL reliability and multiple WPT source power, based on which a power allocation problem is formulated. To solve the formulated non-convex problem, we introduce auxiliary variables and apply successive convex approximation (SCA) technique to the non-convex component. Consequently, a sub-optimal solution can be obtained. Moreover, we extend our design into a dynamic frame structure scenario, i.e., the blocklength allocated for WPT phase and short-packet transmission phase are adjustable, which introduces more flexibility and new challenges to the system design. We provide a joint power and blocklength allocation design to minimize the system overall error probability under the total power and blocklength constraints. To address the high-dimensional optimization problem, auxiliary variables introduction, multiple variable substitutions and SCA technique utilization are exploited to reformulate and efficiently solve the problem. Finally, through numerical results, we validate our analytical model and evaluate the system performance, where a set of guidelines for practical system design are concluded.

eess.SP↗
arXiv2022

Low-Latency Hybrid NOMA-TDMA: QoS-Driven Design Framework

Enabling ultra-reliable and low-latency communication services while providing massive connectivity is one of the major goals to be accomplished in future wireless communication networks. In this paper, we investigate the performance of a hybrid multi-access scheme in the finite blocklength (FBL) regime that combines the advantages of both non-orthogonal multiple access (NOMA) and time-division multiple access (TDMA) schemes. Two latency-sensitive application scenarios are studied, distinguished by whether the queuing behaviour has an influence on the transmission performance or not. In particular, for the latency-critical case with one-shot transmission, we aim at a certain physical-layer quality-of-service (QoS) performance, namely the optimization of the reliability. And for the case in which queuing behaviour plays a role, we focus on the link-layer QoS performance and provide a design that maximizes the effective capacity. For both designs, we leverage the characterizations in the FBL regime to provide the optimal framework by jointly allocating the blocklength and transmit power of each user. In particular, for the reliability-oriented design, the original problem is decomposed and the joint convexity of sub-problems is shown via a variable substitution method. For the effective-capacity-oriented design, we exploit the method of Lagrange multipliers to formulate a solvable dual problem with strong duality to the original problem. Via simulations, we validate our analytical results of convexity/concavity and show the advantage of our proposed approaches compared to other existing schemes.

cs.IT↗