Search arXiv⌕ Search

arXiv subjects

Xu Huang

Publications and source records attributed to Xu Huang.

At least 37 records · Page 2Linked to original sources
arXiv2026

Position: The Hidden Costs and Measurement Gaps of Reinforcement Learning with Verifiable Rewards

Reinforcement learning with verifiable rewards (RLVR) is a practical, scalable way to improve large language models on math, code, and other structured tasks. However, we argue that many headline RLVR gains are not yet well validated because reports often conflate policy improvement with three confounds: (i) budget mismatch between RLVR and baseline evaluations, (ii) attempt inflation and calibration drift that convert abstentions into confident answers, and (iii) benchmark data contamination. Using budget-matched reproductions and partial-prompt contamination probes, we find that several widely cited gaps shrink substantially or disappear once budgets, prompts, and dataset versions are matched and contaminated sets are treated as memorization probes rather than evidence of reasoning. This does not mean that RLVR is ineffective, but it implies that current measurements often overstate capability gains and obscure reliability costs. We therefore propose a compact, tax-aware minimum standard for RLVR training and evaluation: budget-matched saturation curves with variance, calibration, and abstention tracking, a judge-robustness stress test when LLM judges are used, and an explicit contamination screen. With these controls, RLVR remains effective and deployable in verifiable domains, but reasoning gains should be treated as provisional without them.

cs.LG↗
arXiv2026

Normal forms in cubical type theory

This note documents the specification of normal forms in cubical type theory. The definition is already present in the proof of normalization for cubical type theory, but we present it in a more traditional style explicitly for reference.

cs.LO↗
arXiv2026

Similar Users-Augmented Interest Network

Click-through rate (CTR) prediction is one of the core tasks in recommender systems. User behavior sequences, as one of the most effective features, can accurately reflect user preferences and significantly improve prediction accuracy. Richer behavior sequences often enable more comprehensive user profiling, and recent studies have shown that scaling the length of user behavior sequence can yield substantial gains in CTR. However, due to the widespread sparsity in recommender systems, incomplete behavior sequences are common in real-world scenarios. Existing sequential modeling methods often rely solely on the target user's own behavior, and therefore struggle in such scenarios. This paper proposes a novel method called SUIN (Similar Users-augmented Interest Network), which enhances the target user's behavior sequence with behaviors from similar users to enhance the user profile for CTR prediction. Specifically, we use behavior embeddings encoded by a sequence encoder to retrieve users with similar behaviors from a user retrieval pool. The behavior sequences of these similar users are then concatenated with that of the target user in descending order of similarity to construct an augmented sequence. Given that the augmented sequence contains behaviors from multiple users, we propose a user-specific target-aware position encoding, which identifies the source user of each behavior and captures its relative position to the target item. Furthermore, to mitigate the empirically observed noise in similar users' behaviors, we design a user-aware target attention that jointly considers item-item and user-user correlations, fully exploiting the potential of the augmented behavior sequence. Comprehensive experiments on widely-used short-term and long-term sequence benchmark datasets demonstrate that our method significantly outperforms state-of-the-art sequential CTR models.

cs.IR↗
arXiv2026

LLM-Guided Safety Agent for Edge Robotics with an ISO-Compliant Perception-Compute-Control Architecture

Ensuring functional safety in human-robot interaction is challenging because AI perception is inherently probabilistic, whereas industrial standards require deterministic behavior. We present an LLM-guided safety agent for edge robotics, built on an ISO-compliant low-latency perception-compute-control architecture. Our method translates natural-language safety regulations into executable predicates and deploys them through a redundant heterogeneous edge runtime. For fault-tolerant closed-loop execution under edge constraints, we adopt a symmetric dual-modular redundancy design with parallel independent execution for low-latency perception, computation, and control. We prototype the system on a dual-RK3588 platform and evaluate it in representative human-robot interaction scenarios. The results demonstrate a practical edge implementation path toward ISO 13849 Category 3 and PL d using cost-effective hardware, supporting practical deployment of safety-critical embodied AI.

cs.RO↗
arXiv2026

How to Fine-Tune a Reasoning Model? A Teacher-Student Cooperation Framework to Synthesize Student-Consistent SFT Data

A widely adopted strategy for model enhancement is to use synthetic data generated by a stronger model for supervised fine-tuning (SFT). However, for emerging reasoning models like Qwen3-8B, this approach often fails to improve reasoning capabilities and can even lead to a substantial drop in performance. In this work, we identify substantial stylistic divergence between teacher generated data and the distribution of student as a major factor impacting SFT. To bridge this gap, we propose a Teacher-Student Cooperation Data Synthesis framework (TESSY), which interleaves teacher and student models to alternately generate style and non-style tokens. Consequently, TESSY produces synthetic sequences that inherit the advanced reasoning capabilities of the teacher while maintaining stylistic consistency with the distribution of the student. In experiments on code generation using GPT-OSS-120B as the teacher, fine-tuning Qwen3-8B on teacher-generated data leads to performance drops of 3.25% on LiveCodeBench-Pro and 10.02% on OJBench, whereas TESSY achieves improvements of 11.25% and 6.68%.

cs.CL↗
arXiv2026

Agentic LLM Reasoning in a Self-Driving Laboratory for Air-Sensitive Lithium Halide Spinel Conductors

Self-driving laboratories promise to accelerate materials discovery. Yet current automated solid-state synthesis platforms are limited to ambient conditions, thereby precluding their use for air-sensitive materials. Here, we present A-Lab for Glovebox Powder Solid-state Synthesis (A-Lab GPSS), a robotic platform capable of synthesizing and characterizing air-sensitive inorganic materials under strict air-free conditions. By integrating an agentic AI framework into the A-Lab GPSS platform, we structure autonomous experimental design through abductive and inductive reasoning. We deploy this platform to explore the vast compositional space of lithium halide spinel solid-state ionic conductors. Across a synthesis campaign comprising 352 samples with diverse compositions, the system explores a broad chemical space, experimentally realizing 72% of the 171 possible pairwise combinations among the 19 metals considered in this study. Over the course of the campaign, the fraction of compositions exhibiting both good ionic conductivity (> 0.05 mS/cm) and high halide spinel phase purity increases from 1.33% in the first 75 agent-proposed samples to 5.33% in the final 75. Furthermore, by inspecting the AI's reasoning processes, we reveal distinct yet complementary discovery strategies: abductive reasoning interrogates abnormal observations within already explored regions, whereas inductive reasoning expands the search into broader, previously unvisited chemical space. This work establishes a scalable platform for the autonomous discovery of complex, air-sensitive solid-state materials.

cond-mat.mtrl-sci↗
arXiv2026

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

The prevailing Next-Token Prediction (NTP) paradigm has driven the success of large language models through discrete autoregressive modeling. However, contemporary multimodal systems remain language-centric, often treating non-linguistic modalities as external attachments, leading to fragmented architectures and suboptimal integration. To transcend this limitation, we introduce Discrete Native Autoregressive (DiNA), a unified framework that represents multimodal information within a shared discrete space, enabling a consistent and principled autoregressive modeling across modalities. A key innovation is the Discrete Native Any-resolution Visual Transformer (dNaViT), which performs tokenization and de-tokenization at arbitrary resolutions, transforming continuous visual signals into hierarchical discrete tokens. Building on this foundation, we develop LongCat-Next, a native multimodal model that processes text, vision, and audio under a single autoregressive objective with minimal modality-specific design. As an industrial-strength foundation model, it excels at seeing, painting, and talking within a single framework, achieving strong performance across a wide range of multimodal benchmarks. In particular, LongCat-Next addresses the long-standing performance ceiling of discrete vision modeling on understanding tasks and provides a unified approach to effectively reconcile the conflict between understanding and generation. As an attempt toward native multimodality, we open-source the LongCat-Next and its tokenizers, hoping to foster further research and development in the community. GitHub: https://github.com/meituan-longcat/LongCat-Next

cs.CV↗
arXiv2026

TAPO: Translation Augmented Policy Optimization for Multilingual Mathematical Reasoning

Large Language Models (LLMs) have demonstrated remarkable proficiency in English mathematical reasoning, yet a significant performance disparity persists in multilingual contexts, largely attributed to deficiencies in language understanding. To bridge this gap, we introduce Translation-Augmented Policy Optimization (TAPO), a novel reinforcement learning framework built upon GRPO. TAPO enforces an explicit alignment strategy where the model leverages English as a pivot and follows an understand-then-reason paradigm. Crucially, we employ a step-level relative advantage mechanism that decouples understanding from reasoning, allowing the integration of translation quality rewards without introducing optimization conflicts. Extensive experiments reveal that TAPO effectively synergizes language understanding with reasoning capabilities and is compatible with various models. It outperforms baseline methods in both multilingual mathematical reasoning and translation tasks, while generalizing well to unseen languages and out-of-domain tasks.

cs.CL↗
arXiv2026

GTM: A General Time-series Model for Enhanced Representation Learning of Time-Series Data

Despite recent progress in time-series foundation models, challenges persist in improving representation learning and adapting to diverse downstream tasks. We introduce a General Time-series Model (GTM), which advances representation learning via a novel frequency-domain attention mechanism that captures time-granularity-aware features, an aspect underexplored in prior research. We further propose a novel pre-training strategy that unifies reconstruction and autoregressive objectives through a hybrid masking mechanism. Our pre-training strategy, combined with 2D positional encoding and span shuffling, enhances the robustness and generalization of representations. GTM is established as the first generative-task-agnostic model for time-series analysis, enabling seamless adaptation to various generative tasks without any task-specific modifications. Extensive experiments demonstrate that GTM consistently outperforms SOTA models on various generative tasks and achieves strong classification results with minimal adaptation. Furthermore, GTM exhibits clear scaling behavior, with accuracy improving as model size and pre-training data increase.

cs.LG↗
arXiv2026

Position: The Real Barrier to LLM Agent Usability is Agentic ROI

Large Language Model (LLM) agents represent a promising shift in human-AI interaction, moving beyond passive prompt-response systems to autonomous agents capable of reasoning, planning, and goal-directed action. While LLM agents are technically capable of performing a broad range of tasks, not all of these capabilities translate into meaningful usability. This position paper argues that the central question for LLM agent usability is no longer whether a task can be automated, but whether it delivers sufficient Agentic Return on Investment (Agentic ROI). Agentic ROI reframes evaluation from raw performance to a holistic, utility-driven perspective, guiding when, where, and for whom LLM agents should be deployed. Despite widespread application in high-ROI tasks like coding and scientific research, we identify a critical usability gap in mass-market, everyday applications. To address this, we propose a zigzag developmental trajectory: first scaling up to improve information gain and time savings, then scaling down to reduce cost. We present a strategic roadmap across these phases to make LLM agents truly usable, accessible, and scalable in real-world applications.

cs.CL↗
arXiv2026

CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution

Large language model (LLM) agents currently depend on predefined tools or early-stage tool generation, limiting their adaptability and scalability to complex scientific tasks. We introduce CASCADE, a self-evolving agentic framework representing an early instantiation of the transition from "LLM + tool use" to "LLM + skill acquisition". CASCADE enables agents to master complex external tools and codify knowledge through two meta-skills: continuous learning via web search, code extraction, and memory utilization; self-reflection via introspection, knowledge graph exploration, and others. We evaluate CASCADE on SciSkillBench, a benchmark of 116 materials science and chemistry research tasks. CASCADE achieves a 93.3% success rate using GPT-5, compared to 35.4% without evolution mechanisms. We further demonstrate real-world applications in computational analysis, autonomous laboratory experiments, and selective reproduction of published papers. Along with human-agent collaboration and memory consolidation, CASCADE accumulates executable skills that can be shared across agents and scientists, moving toward scalable AI-assisted scientific research.

cs.AI↗
arXiv2026

ToolACE-R: Model-aware Iterative Training and Adaptive Refinement for Tool Learning

Tool learning, which allows Large Language Models (LLMs) to leverage external tools for solving complex user tasks, has emerged as a promising avenue for extending model capabilities. However, existing approaches primarily focus on data synthesis for fine-tuning LLMs to invoke tools effectively, largely ignoring how to fully stimulate the potential of the model. In this paper, we propose ToolACE-R, a novel framework that includes both model-aware iterative training and adaptive refinement for tool learning. ToolACE-R features a model-aware iterative training procedure that progressively adjust training samples based on the model's evolving capabilities to maximize its potential. Additionally, it incorporates self-refinement training corpus which emphasizes LLM's ability to iteratively refine their tool calls, optimizing performance without requiring external feedback. Furthermore, we introduce adaptive self-refinement mechanism for efficient test-time scaling, where the trained model can autonomously determine when to stop the process based on iterative self-refinement. We conduct extensive experiments across several benchmark datasets, showing that ToolACE-R achieves competitive performance compared to advanced API-based models. The performance of tool invocation can be further improved efficiently through adaptive self-refinement. These results highlight the effectiveness and generalizability of ToolACE-R, offering a promising direction for more efficient and scalable tool learning.

cs.CL↗
arXiv2025

Sparse Kalman Identification for Partially Observable Systems via Adaptive Bayesian Learning

Sparse dynamics identification is an essential tool for discovering interpretable physical models and enabling efficient control in engineering systems. However, existing methods rely on batch learning with full historical data, limiting their applicability to real-time scenarios involving sequential and partially observable data. To overcome this limitation, this paper proposes an online Sparse Kalman Identification (SKI) method by integrating the Augmented Kalman Filter (AKF) and Automatic Relevance Determination (ARD). The main contributions are: (1) a theoretically grounded Bayesian sparsification scheme that is seamlessly integrated into the AKF framework and adapted to sequentially collected data in online scenarios; (2) an update mechanism that adapts the Kalman posterior to reflect the updated selection of the basis functions that define the model structure; (3) an explicit gradient-descent formulation that enhances computational efficiency. Consequently, the SKI method achieves accurate model structure selection with millisecond-level efficiency and higher identification accuracy, as demonstrated by extensive simulations and real-world experiments (showing an 84.21\% improvement in accuracy over the baseline AKF).

eess.SY↗
arXiv2025

ACEBench: Who Wins the Match Point in Tool Usage?

Large Language Models (LLMs) have demonstrated significant potential in decision-making and reasoning, particularly when integrated with various tools to effectively solve complex problems. However, existing benchmarks for evaluating LLMs' tool usage face several limitations: (1) limited evaluation scenarios, often lacking assessments in real multi-turn dialogue contexts; (2) narrow evaluation dimensions, with insufficient detailed assessments of how LLMs use tools; and (3) reliance on LLMs or real API executions for evaluation, which introduces significant overhead. To address these challenges, we introduce ACEBench, a comprehensive benchmark for assessing tool usage in LLMs. ACEBench categorizes data into three primary types based on evaluation methodology: Normal, Special, and Agent. "Normal" evaluates tool usage in basic scenarios; "Special" evaluates tool usage in situations with ambiguous or incomplete instructions; "Agent" evaluates tool usage through multi-agent interactions to simulate real-world, multi-turn dialogues. We conducted extensive experiments using ACEBench, analyzing various LLMs in-depth and providing a more granular examination of error causes across different data types.

cs.CL↗
arXiv2025

iTool: Reinforced Fine-Tuning with Dynamic Deficiency Calibration for Advanced Tool Use

Augmenting large language models (LLMs) with external tools is a promising approach to enhance their capabilities, especially for complex tasks. Synthesizing tool-use data through real-world simulations is an effective way to achieve this. However, our investigation reveals that training gains significantly decay as synthetic data increases. The model struggles to benefit from additional synthetic data, which fails to endow it with advanced tool-use capabilities in complex scenarios Moreover, we discovered that the above limitation usually manifests as a fragment deficiency (i.e., parameter errors) in response. To this end, we propose an iterative reinforced fine-tuning strategy designed to alleviate this limitation. This strategy involves: (1) enhancing the diversity of response for synthetic data through path exploration of Monte Carlo Tree Search. (2) iteratively pinpointing the model's deficiency by constructing fine-grained preference pairs, and then improving it by preference optimization algorithms for targeted improvement. The experiments show that our method achieves 13.11% better performance than the same-size base model. It achieves an improvement of 6.5% in complex scenarios compared to the baseline, and it also outperforms larger open-source and closed-source models.

cs.CL↗
arXiv2025

Emu3.5: Native Multimodal Models are World Learners

We introduce Emu3.5, a large-scale multimodal world model that natively predicts the next state across vision and language. Emu3.5 is pre-trained end-to-end with a unified next-token prediction objective on a corpus of vision-language interleaved data containing over 10 trillion tokens, primarily derived from sequential frames and transcripts of internet videos. The model naturally accepts interleaved vision-language inputs and generates interleaved vision-language outputs. Emu3.5 is further post-trained with large-scale reinforcement learning to enhance multimodal reasoning and generation. To improve inference efficiency, we propose Discrete Diffusion Adaptation (DiDA), which converts token-by-token decoding into bidirectional parallel prediction, accelerating per-image inference by about 20x without sacrificing performance. Emu3.5 exhibits strong native multimodal capabilities, including long-horizon vision-language generation, any-to-image (X2I) generation, and complex text-rich image generation. It also exhibits generalizable world-modeling abilities, enabling spatiotemporally consistent world exploration and open-world embodied manipulation across diverse scenarios and tasks. For comparison, Emu3.5 achieves performance comparable to Gemini 2.5 Flash Image (Nano Banana) on image generation and editing tasks and demonstrates superior results on a suite of interleaved generation tasks. We open-source Emu3.5 at https://github.com/baaivision/Emu3.5 to support community research.

cs.CV↗
arXiv2025

Recursive Gaussian Process State Space Model

Learning dynamical models from data is not only fundamental but also holds great promise for advancing principle discovery, time-series prediction, and controller design. Among various approaches, Gaussian Process State-Space Models (GPSSMs) have recently gained significant attention due to their combination of flexibility and interpretability. However, for online learning, the field lacks an efficient method suitable for scenarios where prior information regarding data distribution and model function is limited. To address this issue, this paper proposes a recursive GPSSM method with adaptive capabilities for both operating domains and Gaussian process (GP) hyperparameters. Specifically, we first utilize first-order linearization to derive a Bayesian update equation for the joint distribution between the system state and the GP model, enabling closed-form and domain-independent learning. Second, an online selection algorithm for inducing points is developed based on informative criteria to achieve lightweight learning. Third, to support online hyperparameter optimization, we recover historical measurement information from the current filtering distribution. Comprehensive evaluations on both synthetic and real-world datasets demonstrate the superior accuracy, computational efficiency, and adaptability of our method compared to state-of-the-art online GPSSM techniques.

cs.LG↗
arXiv2025

Robust High-Resolution Multi-Organ Diffusion MRI Using Synthetic-Data-Tuned Prompt Learning

Clinical adoption of multi-shot diffusion-weighted magnetic resonance imaging (multi-shot DWI) for body-wide tumor diagnostics is limited by severe motion-induced phase artifacts from respiration, peristalsis, and so on, compounded by multi-organ, multi-slice, multi-direction and multi-b-value complexities. Here, we introduce a reconstruction framework, LoSP-Prompt, that overcomes these challenges through physics-informed modeling and synthetic-data-driven prompt learning. We model inter-shot phase variations as a high-order Locally Smooth Phase (LoSP), integrated into a low-rank Hankel matrix reconstruction. Crucially, the algorithm's rank parameter is automatically set via prompt learning trained exclusively on synthetic abdominal DWI data emulating physiological motion. Validated across 10,000+ clinical images (43 subjects, 4 scanner models, 5 centers), LoSP-Prompt: (1) Achieved twice the spatial resolution of clinical single-shot DWI, enhancing liver lesion conspicuity; (2) Generalized to seven diverse anatomical regions (liver, kidney, sacroiliac, pelvis, knee, spinal cord, brain) with a single model; (3) Outperformed state-of-the-art methods in image quality, artifact suppression, and noise reduction (11 radiologists' evaluations on a 5-point scale, $p<0.05$), achieving 4-5 points (excellent) on kidney DWI, 4 points (good to excellent) on liver, sacroiliac and spinal cord DWI, and 3-4 points (good) on knee and tumor brain. The approach eliminates navigator signals and realistic data supervision, providing an interpretable, robust solution for high-resolution multi-organ multi-shot DWI. Its scanner-agnostic performance signifies transformative potential for precision oncology.

cs.CV↗