arXiv subjects

Haoning Wang

Publications and source records attributed to Haoning Wang.

9 recordsLinked to original sources

arXiv2026

Rank-Adaptive and Linearly Convergent Frank--Wolfe Method over Spectrahedron via Nonconvex Oracle

For Frank--Wolfe (FW) methods for convex optimization over the spectrahedron, it remains open whether a block-update variant can be linearly convergent when the update rank never exceeds the (unknown) optimal rank $r^*$ at each iteration. Existing block and spectral FW methods require an update rank at least $r^*$---and typically prior knowledge of $r^*$---to obtain a linear rate. This paper develops a rank-adaptive FW method whose update ranks satisfy $\widehat{r}_t\le r_t\le r^*$ at every iteration and which converges linearly after a finite burn-in under quadratic growth and strict complementarity, the two conditions commonly used in spectral FW analyses. The method is built on two designs. The first is a nonconvex spectral oracle, motivated by the geometric connection between the simplex and the spectrahedron; it yields a thresholding rank $r_t$ of the current iterate and a closed-form low-rank solution. Computing $r_t$ exactly, however, requires a full eigendecomposition. The second introduces the efficient rank $\widehat{r}_t$ of the current iterate, a cheap surrogate that inherits the optimality properties of the spectral oracle. The algorithm switches between the thresholding rank and the efficient rank so that the actual FW update uses $\widehat{r}_t$, keeps the per-iteration cost comparable to standard FW, and eventually identifies $r^*$. These results close the gap between low-rank efficiency and fast convergence for Frank--Wolfe methods over the spectrahedron. Numerical experiments demonstrate the advantage of the proposed method.

math.OC↗

arXiv2026

$A^2E$ : An End-to-End Agent Auditing Engine

With the rapid advancement of large language models (LLMs), harnesses have become essential infrastructure for deploying agents across a wide range of domains. The fast-evolving harness ecosystem has also made rigorous capability evaluation increasingly important. However, efficiently building an end-to-end, systematic, and comprehensive evaluation pipeline remains a significant challenge. To address this challenge, we introduce $A^2E$ (Agent Auditing Engine), an end-to-end evaluation engine designed for agent harnesses. $A^2E$ leverages our newly proposed Agent Task Protocol (ATP) to enable the rapid integration of evaluation tasks with different harnesses. Through an automatically instrumented Monitor, it captures and generates standardized execution traces during experiments. In the Evaluation stage, $A^2E$ systematically assesses harness capabilities using a suite of multidimensional metrics. Compared with correctness alone, these metrics provide a more fine-grained characterization of differences among harnesses in execution efficiency, tool use, task planning, and error recovery. Experiments conducted with $A^2E$ further reveal that model-harness combinations exhibit substantial performance variation across different types of tasks, and that no single combination consistently outperforms all others across every task. These findings not only demonstrate the necessity of systematic evaluation but also provide useful guidance for the co-evolution of models and harnesses. Our code is available at https://github.com/datamllab/A2E.

cs.AI↗

arXiv2026

DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer Training

Enabling large language models to achieve stable self-improvement without external expert supervision remains a central challenge in complex reasoning tasks. Existing self-distillation and reinforcement learning methods lack explicit mechanisms for tracking problem-level learning progress and adapting optimization strategies accordingly. Consequently, training may over-optimize easy problems, receive weak supervision from hard problems, and fail to sufficiently explore borderline cases. To resolve these issues, we propose DRIFT, an online self-evolution policy optimization framework for large language models. DRIFT regulates the model's self-improvement process through the joint use of Difficulty Routing and Rhythm Gating. The former identifies the model's learning state at the problem level and dynamically allocates self-distillation and reinforcement learning signals, while the latter refines policy updates at the token level, concentrating exploration on critical reasoning positions. By further incorporating a success buffer and a two-stage curriculum learning strategy, DRIFT preserves high-quality historical experience while progressively guiding the model from reliable behavior acquisition toward stable policy evolution. Evaluated across five benchmarks and three model scales, DRIFT surpasses the peak performance of both GRPO and SDPO across all evaluated metrics. On the average score over the five benchmarks, DRIFT achieves 79.5$\%$, outperforming GRPO by 9.5$\%$ and SDPO by 7.5$\%$, establishing a new state-of-the-art result. Notably, on ToolUse, DRIFT reaches an accuracy of 79.2$\%$, improving over GRPO by 13.5$\%$ and SDPO by 10.7$\%$, setting a new state-of-the-art and substantially outperforming all concurrent methods.

cs.LG↗

arXiv2026

BalanceRAG: Joint Risk Calibration for Cascaded Retrieval-Augmented Generation

Large language models (LLMs) can enhance factuality via retrieval-augmented generation (RAG), but applying RAG to every query is unnecessary when the model-only answer is reliable. This motivates cascaded RAG: each query is first handled by an LLM-only branch, escalated to a RAG fallback only if the primary branch is uncertain, and abstained from when neither branch is sufficiently trustworthy. However, calibrating such cascades stage by stage may be conservative, since the final utility depends on joint uncertainty thresholding of LLM-only and RAG. In this work, we develop BalanceRAG to certify threshold pairs at a target risk level. Given uncertainty scores from the two branches, BalanceRAG frames each threshold pair as an operating point on a two-dimensional lattice and identifies safe operating points using sequential graphical testing. This enables risk-adaptive threshold calibration, controlling the system-level error rate among accepted points, while retaining more examples. Furthermore, BalanceRAG extends to multi-risk calibration, allowing retrieval usage to be bounded together with the selection-conditioned risk. Experiments on three open-domain question answering (QA) benchmarks across multiple LLM backbones demonstrate that BalanceRAG meets prescribed risk levels, preserves higher coverage and more accepted correct examples, and reduces unnecessary retrieval calls compared with always-on RAG.

cs.CL↗

arXiv2026

KAST-BAR: Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Modeling for Universal Neural Interpretation

While EEG foundation models have shown significant potential in universal neural decoding across tasks, their advancement remains constrained by the inadequacy modeling of complex spatiotemporal topology, as well as the inherent modality gap between low-level physiological signals and high-level textual semantics. To address these challenges, we propose a Knowledge-Anchored Semantically-Dynamic Topology Brain Autoregressive Model (KAST-BAR), which dynamically aligns physiological representations derived from multi-level brain topology with an expert-level semantic space. Specifically, we design a Dual-Stream Hierarchical Attention (DSHA) encoder that accurately captures the brain's intrinsic non-Euclidean topology by modeling local temporal dynamics with global spatial contexts. On this basis, a Knowledge-Anchored Semantic Profiler (KASP) is proposed to synthesize physically-grounded and instance-level textual profiles, which subsequently drive a Semantic Text-Aware Refiner (STAR) to dynamically reconstruct EEG representations using Latent Expert Queries. By conducting large-scale pre-training on 21 diverse datasets to build a foundation model, KAST-BAR effectively integrates expert-level medical knowledge into EEG signal representations, consistently achieving superior performance across six downstream tasks. Our code is available at https://github.com/KAST-BAR/KAST-BAR

cs.LG↗

arXiv2025

Exchange Policy Optimization Algorithm for Semi-Infinite Safe Reinforcement Learning

Safe reinforcement learning (RL) aims to optimize long-term performance while adhering to safety requirements. However, many practical applications involve an infinite number of constraints, forming semi-infinite safe RL (SI-safe RL). Such scenarios typically appear when safety conditions must be enforced across an entire continuous parameter space, such as ensuring adequate resource distribution at every spatial location. Existing approaches typically tackle these continuous constraints through naive spatial discretization or stochastic sampling. Such methods inherently suffer from residual violations or provide only probabilistic safety guarantees. Therefore, no current framework can handle infinitely many constraints to provide reliable safety certificates. In this paper, we propose exchange policy optimization (EPO), an algorithmic framework that achieves optimal policy performance with provably bounded safety guarantees. EPO operates by iteratively solving safe RL subproblems restricted to a finite constraint set, adaptively adjusting the active set through constraint expansion and deletion. Specifically, at each iteration, constraints violating a predefined tolerance are added to refine the policy, while those with zero Lagrange multipliers are removed after the policy update. This exchange rule limits the subproblem complexity to ensure computational tractability while driving policy convergence. Theoretically, we establish that, under mild assumptions, EPO achieves finite convergence to a policy that both ensures the optimal reward performance and keeps the global constraint violation within the prescribed tolerance. Furthermore, we derive an upper bound on the required number of iterations and quantify the gap between the obtained policy and the true optimum.

cs.LG↗

arXiv2025

Simplex Frank-Wolfe: Linear Convergence and Its Numerical Efficiency for Convex Optimization over Polytopes

We investigate variants of the Frank-Wolfe (FW) algorithm for smoothing and strongly convex optimization over polyhedral sets, with the goal of designing algorithms that achieve linear convergence while minimizing per-iteration complexity as much as possible. Starting from the simple yet fundamental unit simplex, and based on geometrically intuitive motivations, we introduce a novel oracle called Simplex Linear Minimization Oracle (SLMO), which can be implemented with the same complexity as the standard FW oracle. We then present two FW variants based on SLMO: Simplex Frank-Wolfe and the refined Simplex Frank-Wolfe (rSFW). Both variants achieve a linear convergence rate for all three common step-size rules. Finally, we generalize the entire framework from the unit simplex to arbitrary polytopes. Furthermore, the refinement step in rSFW can accommodate any existing FW strategies such as the well-known away-step and pairwise-step, leading to outstanding numerical performance. We emphasize that the oracle used in our rSFW method requires only one more vector addition compared to the standard LMO, resulting in the lowest per-iteration computational overhead among all known Frank-Wolfe variants with linear convergence.

math.OC↗

arXiv2024

Efficient Online Prediction for High-Dimensional Time Series via Joint Tensor Tucker Decomposition

Real-time prediction plays a vital role in various control systems, such as traffic congestion control and wireless channel resource allocation. In these scenarios, the predictor usually needs to track the evolution of the latent statistical patterns in the modern high-dimensional streaming time series continuously and quickly, which presents new challenges for traditional prediction methods. This paper is the first to propose a novel online algorithm (TOPA) based on tensor factorization to predict streaming tensor time series. The proposed algorithm TOPA updates the predictor in a low-complexity online manner to adapt to the time-evolving data. Additionally, an automatically adaptive version of the algorithm (TOPA-AAW) is presented to mitigate the negative impact of stale data. Simulation results demonstrate that our proposed methods achieve prediction accuracy similar to that of conventional offline tensor prediction methods, while being much faster than them during long-term online prediction. Therefore, TOPA-AAW is an effective and efficient solution method for the online prediction of streaming tensor time series.

math.OC↗

arXiv2024

Low-rank Tensor Autoregressive Predictor for Third-Order Time-Series Forecasting

Recently, tensor time-series forecasting has gained increasing attention, whose core requirement is how to perform dimensionality reduction. In this paper, we establish a least square optimization model by combining tensor singular value decomposition (t-SVD) with autoregression (AR) to forecast third-order tensor time-series, which has great benefit in computational complexity and dimensionality reduction. We divide such an optimization problem using fast Fourier transformation and t-SVD into four decoupled subproblems, whose variables include regressive coefficient, f-diagonal tensor, left and right orthogonal tensors, and propose an efficient forecasting algorithm via alternating minimization strategy, called Low-rank Tensor Autoregressive Predictor (LOTAP), in which each subproblem has a closed-form solution. Numerical experiments indicate that, compared to Tucker-decomposition-based algorithms, LOTAP achieves a speed improvement ranging from $2$ to $6$ times while maintaining accurate forecasting performance in all four baseline tasks. In addition, this algorithm is applicable to a wider range of tensor forecasting tasks because of its more effective dimensionality reduction ability.

math.OC↗