arXiv subjects

Peng Chen

Publications and source records attributed to Peng Chen.

At least 73 records · Page 4Linked to original sources

arXiv2026

Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?

Deep research agents increasingly automate complex information-seeking tasks, producing evidence-grounded reports via multi-step reasoning, tool use, and synthesis. Their growing role demands scalable, reliable evaluation, positioning LLM-as-judge as a supervision paradigm for assessing factual accuracy, evidence use, and reasoning quality. Yet the reliability of these judges for deep research agents remains poorly understood, posing a critical meta-evaluation problem: before deploying LLM judges to supervise research agents, we must first evaluate the judges themselves. Existing meta-evaluations fall short in two ways: (1) reliance on coarse, subjective human-preference agreement; (2) focus on instruction-following or verifiable tasks, leaving open-ended agent executions unexplored. To address these gaps, we introduce REFLECT (REliable Fine-grained LLM judge Evaluation via Controlled inTervention), a meta-evaluation benchmark targeting fine-grained failure detection in agentic environments. REFLECT defines a detailed taxonomy of process- and outcome-level failure modes, instantiated by performing controlled and localized interventions on quality-screened agent execution traces. This yields verifiable, comprehensive, and fine-grained instances for validating the judge models. Our experiments show that current LLM judges remain unreliable: even the best-performing models achieve overall accuracies below 55% across reasoning, tool-use, and report-quality failures, with especially poor performance on evidence verification. Together, our taxonomy and findings expose systematic judge limitations, reveal tradeoffs in cost and reliability, and offer actionable guidance for building more reliable evaluation pipelines for deep research agents.

cs.CL↗

arXiv2026

Domain-Wall Mediated Polarization Switching in Ferroelectric AlScN: Strain Relief and Field-Dependent Dynamics

While scandium-doped aluminum nitride (AlScN) exhibits robust ferroelectricity and excellent thermal stability, its utility is limited by an exceptionally high coercive field ($E_c$) for polarization switching. Unraveling the atomistic switching dynamics is therefore critical for tailoring $E_c$. Here, we combine density functional theory and machine-learning molecular dynamics to elucidate the polarization switching mechanisms in AlScN over various Sc concentrations and applied electric fields. We find that excessive lattice strain strictly prohibits collective polarization switching, but the pre-existing domain walls relieve strain and lead to a distinct switching dynamics -- dictating a field-dependent switching mechanism. At low electric fields, switching occurs via gradual domain-wall propagation consistent with the Kolmogorov-Avrami-Ishibashi model. In contrast, high fields stimulate additional nucleation, driving a rapid, homogeneous reversal process described by the simultaneous non-linear nucleation and growth model. These findings highlight the critical role of domain-wall dynamics and suggest domain engineering as a viable strategy to tailor coercive fields in AlScN and related ferroelectrics.

cond-mat.mtrl-sci↗

arXiv2026

TLX: Hardware-Native, Evolvable MIMW GPU Compiler for Large-scale Production Environments

Modern GPUs increasingly rely on specialized hardware units and asynchronous coordination mechanisms, so performance depends on orchestrating data movement, tensor-core computation, and synchronization rather than exposing more thread-level parallelism. This creates a programming-model tension: if too much execution structure is hidden, the compiler must catch up to new hardware mechanisms; if too much is exposed, the burden of orchestration falls back onto the programmer. We present TLX (Triton Low-level Language Extensions), built around MIMW (Multi-Instruction, Multi-Warp), which expresses orchestration at warp-group granularity while preserving Triton's productive blocked programming model for regular computation. TLX realizes this idea as an embedded extension to Triton, exposing explicit interfaces for multi-warp execution, local-memory orchestration, asynchronous operations, and cluster-aware control. Our evaluation shows that TLX supports substantial customization with limited development effort while remaining competitive with state-of-the-art implementations. TLX-authored kernels have been deployed in large-scale training and inference production systems. Our code is open sourced at https://github.com/facebookexperimental/triton.

cs.AR↗

arXiv2026

FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing

Library fuzzing is essential for hardening the software supply chain, but adopting it at scale remains expensive. Practitioners still spend substantial effort on environment setup, struggle to generate harnesses that respect intricate API constraints, and lack reliable means to tell genuine library bugs from harness-induced crashes. Recent LLM-based systems automate parts of this pipeline, yet they typically operate as one-shot code generators that ignore runtime feedback, which limits both the depth of code they reach and the validity of the bugs they report. We argue that effective library fuzzing is iterative by nature: each campaign exposes new coverage bottlenecks and crashes, and the next campaign should evolve from these signals rather than restart from scratch. Building on this insight, we present FuzzAgent, a multi-agent system that turns library fuzzing into an evolutionary process, in which a team of specialized agents collaborates over the full fuzzing lifecycle and grounds every decision in concrete runtime evidence, so that the harness suite is successively refined toward deeper coverage and higher-fidelity crash analysis across rounds. We evaluate FuzzAgent on 20 real-world C/C++ libraries against four state-of-the-art baselines (OSS-Fuzz, OSS-Fuzz-Gen, PromptFuzz, and PromeFuzz). FuzzAgent completes the full fuzzing lifecycle for all 20 libraries without human intervention and reaches 179619 branches, exceeding OSS-Fuzz, PromptFuzz, PromeFuzz, and OSS-Fuzz-Gen by 45.1%, 73.2%, 92.1%, and 191.2%, respectively. FuzzAgent also identifies 102 genuine library bugs, 78 of which have already been acknowledged and fixed by upstream maintainers.

cs.SE↗

arXiv2026

SHIRO: Near-Optimal Communication Strategies for Distributed Sparse Matrix Multiplication

Distributed Sparse Matrix-Matrix Multiplication (SpMM) is a fundamental operation in high-performance computing and deep learning applications. The major performance bottleneck in distributed SpMM lies in substantial communication overhead, which limits both performance and scalability. In this paper, we identify two key sources of communication inefficiency in distributed SpMM: redundant data transfer due to sparsity unawareness, and suboptimal utilization of hierarchical network topology. To address these, we propose (1) a fine-grained, sparsity-aware communication strategy that reduces communication overhead by exploiting the sparsity pattern of the sparse matrix, and (2) a hierarchical communication strategy that maps the sparsity-aware strategy onto two-tier GPU network architectures, minimizing redundant data movement across slower inter-node links. We implement these optimizations in a comprehensive distributed SpMM framework, \method{}. Extensive evaluations on real-world datasets show that \method{} demonstrates strong scalability up to 128 GPUs, achieving geometric mean speedups of 221.5$\times$, 56.0$\times$, 23.4$\times$, and 8.8$\times$ in SpMM over four state-of-the-art baselines (CAGNET, SPA, BCL, and CoLa, respectively) at this scale.

cs.DC↗

arXiv2026

Toward AI-Driven Digital Twins for Metropolitan Floods: A Conditional Latent Dynamics Network Surrogate of the Shallow Water Equations

AI-driven flood digital twins demand fast hydrodynamic surrogates for ensemble forecasting and observation assimilation. Yet even GPU-accelerated two-dimensional shallow water equation (SWE) solvers still require $\sim 55$ minutes per $96$-hour run on a $\sim 4.2$-million-active-cell metropolitan basin (the Des~Plaines River basin at $30\,\mathrm{m}$ resolution), making such workloads prohibitive at native resolution. We present the Conditional Latent Dynamics Network (CLDNet): a low-dimensional latent neural ODE driven by rainfall, paired with a coordinate-based decoder conditioned on static terrain (elevation, slope, Manning roughness) that reconstructs depth and discharge at arbitrary query points. Pointwise decoding decouples memory from grid size and handles irregular watersheds natively, enabling metropolitan-scale training on a single compute node and direct queries at exact gauge coordinates without raster snapping. We evaluate CLDNet on a synthetic $250{,}000$-cell Texas benchmark and on a new Des~Plaines case study of $114$ real-rainfall Stage~IV storms whose reference simulator we validate against United States Geological Survey (USGS) gauges at the April~2013 flood-of-record (Nash--Sutcliffe efficiency $0.57$--$0.94$ on mean-recentered water-surface elevation). CLDNet roughly halves the relative root-mean-squared error of an unconditional baseline, outperforms regular-grid VAE--ConvLSTM and FNO baselines on the Texas benchmark (both presuppose a Cartesian grid and do not apply to the irregular Des~Plaines watershed), reaches a critical success index of $\approx 86\%$ at the $0.5\,\mathrm{m}$ inundation threshold, and produces a full $96$-hour basin-wide forecast in $\sim 29$ seconds -- a $\sim 115\times$ speedup.

cs.LG↗

arXiv2026

TRACE: Temporal Routing with Autoregressive Cross-channel Experts for EEG Representation Learning

Learning transferable representations for electroencephalography (EEG) remains challenging because EEG signals are inherently multi-channel and non-stationary. Channels observed at the same time provide coupled measurements of neural activity, while the relevant temporal dynamics vary across contexts. This structure is poorly matched by architectures that apply uniform computation across time or route each channel patch independently. To this end, we propose TRACE, an autoregressive EEG pre-training framework that predicts future EEG patches from causal context while performing temporally adaptive and cross-channel coherent computation. At each temporal step, TRACE derives an expert routing decision from the causal cross-channel history and applies it jointly to all channels at that step. This preserves instantaneous cross-channel coherence while allowing different temporal regimes to activate different computation. Since routing is defined over the available channel set and causal temporal context, TRACE is compatible with heterogeneous pre-training across corpora with different channel counts, montages, sequence lengths, and recording domains. Across eight downstream EEG benchmarks, TRACE is evaluated in both settings: when downstream domains are seen only as unlabeled pre-training data and when downstream datasets are completely unseen during pre-training. It obtains the best results on several benchmarks while remaining competitive on motor imagery and clinical event classification tasks, with ablations supporting the importance of cross-channel temporal routing.

cs.LG↗

arXiv2026

Towards Explainable Industrial Anomaly Detection via Knowledge-Guided Latent Reasoning

Industrial anomaly detection demands precise reasoning over fine-grained defect patterns. However, existing multimodal large language models (MLLMs), pretrained on general-domain data, often struggle to capture category-specific anomalies, thereby limiting both detection accuracy and interpretability. To address these limitations, we propose Reason-IAD, a knowledge-guided dynamic latent reasoning framework for explainable industrial anomaly detection. Reason-IAD comprises two core components. First, a retrieval-augmented knowledge module incorporates category-specific textual descriptions into the model input, enabling context-aware reasoning over domain-specific defects. Second, an entropy-driven latent reasoning mechanism conducts iterative exploration within a compact latent space using optimizable latent think tokens, guided by an entropy-based reward that encourages confident and stable predictions. Furthermore, a dynamic visual injection strategy selectively incorporates the most informative image patches into the latent sequence, directing the reasoning process toward regions critical for anomaly detection. Extensive experimental results demonstrate that Reason-IAD consistently outperforms state-of-the-art methods across multiple tasks. The code will be publicly available at https://github.com/chenpeng052/Reason-IAD.

cs.CV↗

arXiv2026

A$^2$TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping

Reinforcement learning for agentic large language models (LLMs) typically relies on a sparse, trajectory-level outcome reward, making it difficult to evaluate the contribution of individual tool-calls within multi-turn interactions. Existing approaches to such process credit assignment either depend on separate external process reward models that introduce additional consumption, or tree-based structural rollout that merely redistributes the outcome signal while constraining trajectory diversity. A promising alternative leverages the per-turn change in the policy's predicted probability of the ground-truth, termed Information Gain (IG), as an intrinsic process signal without an external evaluator. However, prior work on leveraging IG signals within the RL training loop faces three systematic challenges: normalizing across turns that face heterogeneous positional contexts can distort the relative standing of individual turns, accumulating a variable number of terms causes advantage magnitudes to drift with trajectory depth, and a fixed clipping range governs policy updates identically for turns with vastly different IG signals. In this paper, we propose A$^2$TGPO (Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping), which retains IG as the intrinsic signal but re-designs how it is normalized, accumulated, and consumed: (i) turn-group normalization: normalizes IG within each (prompt, turn-index) group so that each turn is compared only against peers at the same interaction depth; (ii) variance-rescaled discounted accumulation: divides cumulative normalized IG by square root of accumulated terms to keep advantage magnitudes comparable across turn positions; and (iii) adaptive turn-level clipping: modulates each turn's clipping range based on its normalized IG, widening the update region for informative turns and narrowing it for uninformative ones.

cs.CL↗

arXiv2026

SiriusHelper: An LLM Agent-Based Operations Assistant for Big Data Platforms

Big data platforms are widely used in modern enterprises, and an in-production intelligent assistant is increasingly important to help users quickly find actionable guidance and reduce operational burden. While recent LLM+RAG assistants provide a natural interface, they face practical challenges in real deployments: limited scenario coverage across both general consultation and domain-specific troubleshooting workflows, inefficient knowledge access due to inadequate multi-hop retrieval and flat knowledge organization, and high maintenance cost because escalated tickets are unstructured and hard to convert into assistant improvements and reusable SOPs. In this paper, we present SiriusHelper, a deployed intelligent assistant for big data platforms. SiriusHelper serves as a unified online assistant that automatically identifies user intent and routes queries to the right handling path, including dedicated expert workflows for specialized scenarios (e.g., SQL execution diagnosis). To support complex troubleshooting, SiriusHelper combines a DeepSearch-driven mechanism with a priority-based hierarchical knowledge base to enable multi-hop retrieval without context overload, thus improving answer reliability and latency. To reduce expert overhead, SiriusHelper further introduces automated ticket understanding and SOP distillation: it diagnoses the assistant failure reason (e.g., missing knowledge or wrong routing) and extracts domain-specific SOPs to continuously enrich the knowledge base. Experiments and online deployment on Tencent Big Data platform show that SiriusHelper outperforms representative alternatives and reduces online ticket volume by 20.8\%.

cs.DB↗

arXiv2026

A Synergistic CNN-Transformer Network with Pooling Attention Fusion for Hyperspectral Image Classification

In the hyperspectral image (HSI) classification task, each pixel is categorized into a specific land-cover category or material. Convolutional neural networks (CNNs) and transformers have been widely used to extract local and non-local features in HSI classification. Recent works have utilized a multi-scale vision transformer (ViT) to enhance spectral feature capture and yield promising results. However, most existing methods still face challenges in the effective joint use of spatial-spectral information and in preserving information across layers during the propagation process. To address these issues, we propose a synergistic CNN-Transformer network with pooling attention fusion for HSI classification, which collaboratively utilizes CNNs and ViT to process spatial and spectral features separately. Specifically, we propose a Twin-Branch Feature Extraction (TBFE) module, which employs 3D and 2D convolution in parallel to comprehensively extract spectral and spatial features from HSI. A hybrid pooling attention (HPA) module is designed to aggregate spatial attention. Moreover, a cascade transformer encoder is employed for global spectral feature extraction, and a simple yet efficient cross-layer feature fusion (CFF) module is designed to reduce the loss of crucial information in the previous network layers. Extensive experiments are conducted on several representative datasets to demonstrate the superior performance of our proposed method compared to the state-of-the-art works. Code is available at https://github.com/chenpeng052/SCT-Net.git.

cs.CV↗

arXiv2026

Toward Robust and Efficient ML-Based GPU Caching for Modern Inference

In modern GPU inference, cache efficiency remains a major bottleneck, and heuristic policies such as \textsc{LRU} can perform far worse than the offline optimum. Existing learning-based caching systems improve hit rates mainly through predictor design, but often follow learned predictions blindly, making performance unreliable when predictions are inaccurate. In contrast, emerging learning-augmented caching algorithms~\cite{pmlr-v80-lykouris18a,mitzenmacher2022algorithms} provide performance guarantees by carefully integrating predictions into caching policies, achieving both \emph{consistency} (near-optimality under perfect predictions) and \emph{robustness} (bounded worst-case performance under prediction errors). However, deployment remains challenging. A practical algorithm should satisfy strict time and space efficiency constraints, which some theoretical work overlooks, while also incurring low deployment overhead. We propose learning-augmented LRU, a deployment-oriented learning-augmented caching algorithm that guarantees \emph{1-consistency} and \emph{$O(k)$-robustness}, incurs low time and space overhead, and maintains strong compatibility. We further build a GPU cache, called \textsc{LCR}, on top of learning-augmented LRU to benefit from its theoretical guarantees and translate them into practical performance. In experiments, \textsc{LCR} reduces P99 time-to-first-token (TTFT) by up to 28.3\% on LLM workloads and increases throughput by up to 24.2\% on deep learning recommendation (DLRM) workloads. Even with poor predictions, performance degrades gracefully and remains close to \textsc{LRU}, demonstrating robustness with practical value.

cs.LG↗

arXiv2026

M100: An Orchestrated Dataflow Architecture Powering General AI Computing

As deep learning-based AI technologies gain momentum, the demand for general-purpose AI computing architectures continues to grow. While GPGPU-based architectures offer versatility for diverse AI workloads, they often fall short in efficiency and cost-effectiveness. Various Domain-Specific Architectures (DSAs) excel at particular AI tasks but struggle to extend across broader applications or adapt to the rapidly evolving AI landscape. M100 is Li Auto's response: a performant, cost-effective architecture for AI inference in Autonomous Driving (AD), Large Language Models (LLMs), and intelligent human interactions, domains crucial to today's most competitive automobile platforms. M100 employs a dataflow parallel architecture, where compiler-architecture co-design orchestrates not only computation but, more critically, data movement across time and space. Leveraging dataflow computing efficiency, our hardware-software co-design improves system performance while reducing hardware complexity and cost. M100 largely eliminates caching: tensor computations are driven by compiler- and runtime-managed data streams flowing between computing elements and on/off-chip memories, yielding greater efficiency and scalability than cache-based systems. Another key principle was selecting the right operational granularity for scheduling, issuing, and execution across compiler, firmware, and hardware. Recognizing commonalities in AI workloads, we chose the tensor as the fundamental data element. M100 demonstrates general AI computing capability across diverse inference applications, including UniAD (for AD) and LLaMA (for LLMs). Benchmarks show M100 outperforms GPGPU architectures in AD applications with higher utilization, representing a promising direction for future general AI computing.

cs.LG↗

arXiv2026

Evolution of topological phases in atomically thin WTe2 films

Topological materials ranging from topological insulators to semimetals host many novel quantum phenomena including quantum spin Hall effect and topological Fermi arcs. Transitions between these topological phases have attracted much research interest. We performed angle-resolved photoemission spectroscopy (ARPES) on WTe2 ranging from a monolayer to the bulk and reveal the evolution of the electronic structure and the band gap. Notably, the gap observed in the monolayer system is suppressed in the three layers, where the film becomes metallic. Variations in the topological properties with thickness are demonstrated by the first-principles calculations. Topological Z2 invariant is shown to oscillate between 1 and 0 with the addition of layers, originating from the interlayer coupling-induced change in band crossing. The system evolves into a Weyl semimetal when the conduction and valence bands touch near the Fermi level and the topological nature is described by the Chern number. Our findings demonstrate the non-monotonic dependence of topological states on dimensionality and how layer-driven electronic band reconfiguration leads to phase transitions in solids.

cond-mat.mes-hall↗

arXiv2026

Valve: Production Online-Offline Inference Colocation with Jointly-Bounded Preemption Latency and Rate

LLM inference powers latency-critical production services nowadays. The bursty nature of inference traffic results in over-provisioning, which in turn leads to resource underutilization. While online-offline colocation promises to utilize idle capacity, broad production deployment must overcome two major challenges: (i) large online interference due to slow or frequent preemptions, and (ii) extensive frameworks and drivers modifications, to colocate different models and support preemptions. We present Valve, a production-friendly colocation system that jointly bounds preemption latency and preemption rate. Specifically, Valve enables sub-millisecond compute preemption at most once per online request, and rate-limited sub-layer memory reclamation. These guaranties are provided by a GPU runtime that combines channel-controlled compute isolation, page-fault-free memory reclamation, and dynamic memory reservation. Critically, Valve is practical to deploy, requiring one line of driver modification and 20 lines of framework patch. Deployed on 8,054 GPUs in production, Valve improves cluster utilization by 34.6%, which translates to a 2,170 GPU save. This efficiency gains is achieved with minimal online interference, incurring <5% TTFT increase and <2% TPOT increase across workloads.

cs.OS↗

arXiv2026

RBF-Generated Finite Difference Method Coupled with Quadratic Programming for Solving PDEs on Surfaces with Derivative Boundary Conditions

Derivative boundary conditions introduce challenges for mesh-free discretizations of PDEs on surfaces, especially when the domain is represented by randomly sampled point clouds. The recently developed two-step tangent-space RBF-generated finite difference (RBF-FD) method provides high accuracy on closed surfaces. However, it may lose stability when applied directly to surface PDEs with derivative boundary conditions. To enhance numerical stability, we develop a mesh-free method that couples the two-step tangent-space RBF-FD discretization with a quadratic programming (QP) procedure to stabilize the operator approximation for interior points near boundaries. For boundary points, we construct restricted nearest-neighbor stencils biased in the co-normal direction and employ a constrained quadratic program to approximate outward co-normal derivatives. The resulting method avoids using ghost points and does not require quasi-uniform node distributions. We validate the approach on elliptic problems, eigenvalue problems, time-dependent diffusion equations, and elliptic interface problems on surfaces with boundary. Numerical experiments demonstrate stable performance and high-order accuracy across a variety of surfaces.

math.NA↗

arXiv2026

Learning Rollout from Sampling:An R1-Style Tokenized Traffic Simulation Model

Learning diverse and high-fidelity traffic simulations from human driving demonstrations is crucial for autonomous driving evaluation. The recent next-token prediction (NTP) paradigm, widely adopted in large language models (LLMs), has been applied to traffic simulation and achieves iterative improvements via supervised fine-tuning (SFT). However, such methods limit active exploration of potentially valuable motion tokens, particularly in suboptimal regions. Entropy patterns provide a promising perspective for enabling exploration driven by motion token uncertainty. Motivated by this insight, we propose a novel tokenized traffic simulation policy, R1Sim, which represents an initial attempt to explore reinforcement learning based on motion token entropy patterns, and systematically analyzes the impact of different motion tokens on simulation outcomes. Specifically, we introduce an entropy-guided adaptive sampling mechanism that focuses on previously overlooked motion tokens with high uncertainty yet high potential. We further optimize motion behaviors using Group Relative Policy Optimization (GRPO), guided by a safety-aware reward design. Overall, these components enable a balanced exploration-exploitation trade-off through diverse high-uncertainty sampling and group-wise comparative estimation, resulting in realistic, safe, and diverse multi-agent behaviors. Extensive experiments on the Waymo Sim Agent benchmark demonstrate that R1Sim achieves competitive performance compared to state-of-the-art methods.

cs.RO↗

arXiv2026

Towards Multimodal Time Series Anomaly Detection with Semantic Alignment and Condensed Interaction

Time series anomaly detection plays a critical role in many dynamic systems. Despite its importance, previous approaches have primarily relied on unimodal numerical data, overlooking the importance of complementary information from other modalities. In this paper, we propose a novel multimodal time series anomaly detection model (MindTS) that focuses on addressing two key challenges: (1) how to achieve semantically consistent alignment across heterogeneous multimodal data, and (2) how to filter out redundant modality information to enhance cross-modal interaction effectively. To address the first challenge, we propose Fine-grained Time-text Semantic Alignment. It integrates exogenous and endogenous text information through cross-view text fusion and a multimodal alignment mechanism, achieving semantically consistent alignment between time and text modalities. For the second challenge, we introduce Content Condenser Reconstruction, which filters redundant information within the aligned text modality and performs cross-modal reconstruction to enable interaction. Extensive experiments on six real-world multimodal datasets demonstrate that the proposed MindTS achieves competitive or superior results compared to existing methods. The code is available at: https://github.com/decisionintelligence/MindTS.

cs.LG↗