Searcharxiv⌕ Search

arXiv subjects

Wanrong Yang

Publications and source records attributed to Wanrong Yang.

9 recordsLinked to original sources

When Self-Consistency Hurts: The Hidden Cost of Majority Voting in Small Language Models

We study prompted chain-of-thought (CoT) with self-consistency (SC), i.e. sampling N traces and plurality-voting, on small language models, a regime where per-query compute budgets are tight yet SC is commonly applied with a fixed sample budget inherited from large-model practice, regardless of instance difficulty. Across two model families (Qwen-2.5-0.5B, Gemma-3-1B) at FP16 and MLX-Q4 (4-bit quantisation in Apple's MLX framework), on GSM8K and MATH-500, we run 8 per-task and 4 task-pooled experiments at n=200-400 with 1,000x paired-bootstrap confidence intervals (CIs). Our first result is an upper bound: an oracle gate deciding per prompt whether to invoke SC reaches 109-174% of always-SC's accuracy at 23-30% of its compute in all 12/12 cases, so at N=5 always-SC is dominated everywhere on our grid. That margin is exactly the rate at which SC flips correct greedy answers to wrong, here 3-10.5% of prompts, which on Qwen-Q4 x MATH-500 exceeds the wrong-to-right rate and leaves always-SC 3 pt worse than always-greedy. Our second result is a deployable approximation: a gate over greedy-pass signals skips 45-99% of SC calls, with bootstrap CI half-widths under 5 pt, removing 36-79% of always-SC compute. Accuracy retention at those operating points has point estimates of 98.1-98.8%, which we report as point estimates because their CIs are wide (lower bounds 76-86%) over an SC accuracy of only 15-36%. The evidence covers N=5 on two <=1B families and two math benchmarks, which is the scope we claim. Code is available at https://github.com/heywanrong/SiftSC.

cs.AI↗

On decay of solutions to the anisotropic Boussinesq equations near the hydrostatic balance in half space $\mathbb{R}_+^3$

The system of the Boussinesq equations is one of the most important models for geophysical fluids. This paper focuses on the initial-boundary problem of the 3D incompressible anisotropic Boussinesq system with horizontal dissipation. The goal here is to assess the stability property and large-time behavior of perturbations near the hydrostatic balance. By utilizing the structure of the system, the energy methods and the means of bootstrapping argument, we prove the global stability property in the Sobolev space $H^3(\mathbb{R}^3_+)$. After taking a Fourier transform in $x_h = (x_1, x_2)$ and Fourier cosine and sine transforms in $x_3$ for the system, we obtain the decay rates for the global solution itself as well as its derivatives.

math.AP↗

Sharp linear stability and the absence of enhanced dissipation for Kolmogorov flow in the 2D Navier--Stokes equations with horizontal dissipation

We study the linearized dynamics of the Kolmogorov flow $U^{(0)}=(a\sin x_2,0)$ for the two-dimensional incompressible Navier--Stokes equations with horizontal dissipation $ν\partial_1^2$. Unlike the fully dissipative case, this anisotropic system admits $U^{(0)}$ as an exact unforced steady state. On each horizontal Fourier mode $k$, the dissipation reduces to the scalar $-νk^2$ and commutes with the advection, so that the linearized semigroup factors exactly into $e^{-νk^2t}$ times the inviscid Euler group. For $|k|>1$, we prove two-sided bounds showing that the decay rate is exactly $νk^2$, uniformly in the shear amplitude $a$; hence no enhanced dissipation occurs. This reflects a fundamental mismatch: the shear transfers enstrophy to high vertical frequencies, which horizontal dissipation does not detect. At the critical modes $|k|=1$, the inviscid group grows like $\sqrt{2at}$, producing a transient amplification of size $(a/eν)^{1/2}$ before decay at the rate $ν$. The horizontally independent modes form an infinite-dimensional undamped kernel. For $0<|k|<1$, the viscous spectrum is an exact translate of the inviscid one, and the mode is linearly unstable if and only if $aΛ(k)>νk^2$. In particular, when $L>2π$, the flow is linearly unstable for all sufficiently large $a$.

math.AP↗

Prospective Interpretation Risk: Principled Communication Control Between LLMs

Large language model (LLM) agentic systems increasingly rely on models communicating with one another, yet existing uncertainty and multi-agent methods rarely estimate how a particular receiver will interpret a message before it is sent. This matters in heterogeneous systems, where capable receivers can reconstruct different tasks from the same message. We model this as a sender-receiver problem with a latent receiver type and define prospective interpretation risk (PIR): the probability that a receiver reconstructs a task other than intended. Rather than model an LLM's full input-output behaviour, we use black-box probes relating messages, intended tasks, and receiver-specific reconstructions, yielding scalable supervision while separating interpretation from downstream capability failure. Offline, heterogeneous frozen receivers provide supervision for receiver-conditioned risk and the effects of predefined mutable message features. At deployment, history induces a posterior over receiver types, guiding message revision and selection. We introduce value of interpretation information (VoII), querying for receiver information only when its expected communication benefit exceeds its cost. Our theory characterises when receiver information has decision value and bounds such queries. Empirically, interpretation-failure rates vary by 4-13x across receivers. Receiver information reduces PIR calibration error by 68% relative to a receiver-agnostic predictor, largely by correcting receiver-specific risk levels. PIR-guided revision reduces interpretation failure by 44% relative to the original message and 40% relative to a generic rewrite, mostly through a repair that helps every receiver. VoII outperforms information-gain and random querying at matched cost on the interpretation objective it optimises, lowering interpretation failure from 3.84% to 3.79% while querying 18.2% of episodes.

cs.MA↗

Learning Multi-Timescale Interventions under Safety and Resource Constraints

Many sequential decision problems offer qualitatively different ways of influencing the environment: some interventions act immediately, whereas others induce persistent effects that continue to shape future states long after the decision that initiated them. An agent must then decide jointly when to intervene, which temporal mode to use and how strongly, while accounting for residual effects and limited intervention resources. We introduce MINT: Multi-timescale Intervention Network Training. Persistent effects are carried by an augmented intervention state that accumulates and decays, while a structured policy separates intervention-mode selection from conditional control. Unlike temporal abstractions that extend policy execution, persistent-effect interventions remain part of the environment dynamics and may overlap with later interventions. We show that the augmented state is a sufficient statistic for the intervention history, preserving the Markov property, and establish Bellman contraction and almost-sure convergence of a tabular Q-learning instance. Across persistent-control MuJoCo locomotion, stochastic inventory management, and a physiologically grounded Type 1 Diabetes Mellitus (T1DM) simulator, MINT attains the best mean primary metric on two of three benchmarks while using fewer intervention activations than an identically augmented flat policy. Its return advantage is present at every binding intervention budget and narrows to parity in the unconstrained reference setting. In T1DM it achieves $90.9\pm0.9\%$ time in range with zero time below range, improving on the strongest baseline by $21.5\%$ points. Code, benchmarks and the configuration for every reported run are available at https://github.com/heywanrong/mint-rl.

cs.LG↗

Empowering Locally Deployable Medical Agent via State Enhanced Logical Skills for FHIR-based Clinical Tasks

While Large Language Models demonstrate immense potential as proactive Medical Agents, their real-world deployment is severely bottlenecked by data scarcity under privacy constraints. To overcome this, we propose State-Enhanced Logical-Skill Memory (SELSM), a training-free framework that distills simulated clinical trajectories into entity-agnostic operational rules within an abstract skill space. During inference, a Query-Anchored Two-Stage Retrieval mechanism dynamically fetches these entity-agnostic logical priors to guide the agent's step-by-step reasoning, effectively resolving the state polysemy problem. Evaluated on MedAgentBench -- the only authoritative high-fidelity virtual EHR sandbox benchmarked with real clinical data -- SELSM substantially elevates the zero-shot capabilities of locally deployable foundation models (30B--32B parameters). Notably, on the Qwen3-30B-A3B backbone, our framework completely eliminates task chain breakdowns to achieve a 100\% completion rate, boosting the overall success rate by an absolute 22.67\% and significantly outperforming existing memory-augmented baselines. This study demonstrates that equipping models with a dynamically updatable, state-enhanced cognitive scaffold is a privacy-preserving and computationally efficient pathway for local adaptation of AI agents to clinical information systems. While currently validated on FHIR-based EHR interactions as an initial step, the entity-agnostic design of SELSM provides a principled foundation toward broader clinical deployment.

cs.AI↗

A Survey for Deep Reinforcement Learning Based Network Intrusion Detection

Cyber-attacks are becoming increasingly sophisticated and frequent, highlighting the importance of network intrusion detection systems. This paper explores the potential and challenges of using deep reinforcement learning (DRL) in network intrusion detection. It begins by introducing key DRL concepts and frameworks, such as deep Q-networks and actor-critic algorithms, and reviews recent research utilizing DRL for intrusion detection. The study evaluates challenges related to model training efficiency, detection of minority and unknown class attacks, feature selection, and handling unbalanced datasets. The performance of DRL models is comprehensively analyzed, showing that while DRL holds promise, many recent technologies remain underexplored. Some DRL models achieve state-of-the-art results on public datasets, occasionally outperforming traditional deep learning methods. The paper concludes with recommendations for enhancing DRL deployment and testing in real-world network scenarios, with a focus on Internet of Things intrusion detection. It discusses recent DRL architectures and suggests future policy functions for DRL-based intrusion detection. Finally, the paper proposes integrating DRL with generative methods to further improve performance, addressing current gaps and supporting more robust and adaptive network intrusion detection systems.

cs.CR↗

Fault Tolerant Multi-Agent Learning with Adversarial Budget Constraints

We study robustness to agent malfunctions in cooperative multi-agent reinforcement learning (MARL), a failure mode that is critical in practice yet underexplored in existing theory. We introduce MARTA, a plug-and-play robustness layer that augments standard MARL algorithms with a Switcher-Adversary mechanism which selectively induces malfunctions in performance-critical states. This formulation defines a fault-switching $(N+2)$-player Markov game in which the Switcher chooses when and which agent fails, and the Adversary controls the resulting faulty behaviour via random or worst-case policies. We develop a Q-learning-type scheme and show that the associated Bellman operator is a contraction, yielding existence and uniqueness of the minimax value, convergence to a Markov perfect equilibrium. MARTA integrates seamlessly with MARL algorithms without architectural modification and consistently improves robustness across Traffic Junction (TJ), Level-Based Foraging (LBF), MPE SimpleTag, and SMAC (v2). In these domains, MARTA achieves large gains in final performance of up to 116.7\% in SMAC, 21.4\% in MPE SimpleTag, and 44.6\% in LBF, while significantly reducing failure rates under train-test mismatched fault regimes. These results establish MARTA as a theoretically grounded and practically deployable mechanism for fault-tolerant MARL.

cs.MA↗

Advancing Cross-Organ Domain Generalization with Test-Time Style Transfer and Diversity Enhancement

Deep learning has made significant progress in addressing challenges in various fields including computational pathology (CPath). However, due to the complexity of the domain shift problem, the performance of existing models will degrade, especially when it comes to multi-domain or cross-domain tasks. In this paper, we propose a Test-time style transfer (T3s) that uses a bidirectional mapping mechanism to project the features of the source and target domains into a unified feature space, enhancing the generalization ability of the model. To further increase the style expression space, we introduce a Cross-domain style diversification module (CSDM) to ensure the orthogonality between style bases. In addition, data augmentation and low-rank adaptation techniques are used to improve feature alignment and sensitivity, enabling the model to adapt to multi-domain inputs effectively. Our method has demonstrated effectiveness on three unseen datasets.

cs.CV↗