arXiv subjects

Dan Zhang

Publications and source records attributed to Dan Zhang.

At least 55 records · Page 3Linked to original sources

arXiv2026

Blue Data Intelligence Layer: Streaming Data and Agents for Multi-source Multi-modal Data-Centric Applications

NL2SQL systems aim to address the growing need for natural language interaction with data. However, real-world information rarely maps to a single SQL query because (1) users express queries iteratively (2) questions often span multiple data sources beyond the closed-world assumption of a single database, and (3) queries frequently rely on commonsense or external knowledge. Consequently, satisfying realistic data needs require integrating heterogeneous sources, modalities, and contextual data. In this paper, we present Blue's Data Intelligence Layer (DIL) designed to support multi-source, multi-modal, and data-centric applications. Blue is a compound AI system that orchestrates agents and data for enterprise settings. DIL serves as the data intelligence layer for agentic data processing, to bridge the semantic gap between user intent and available information by unifying structured enterprise data, world knowledge accessible through LLMs, and personal context obtained through interaction. At the core of DIL is a data registry that stores metadata for diverse data sources and modalities to enable both native and natural language queries. DIL treats LLMs, the Web, and the User as source 'databases', each with their own query interface, elevating them to first-class data sources. DIL relies on data planners to transform user queries into executable query plans. These plans are declarative abstractions that unify relational operators with other operators spanning multiple modalities. DIL planners support decomposition of complex requests into subqueries, retrieval from diverse sources, and finally reasoning and integration to produce final results. We demonstrate DIL through two interactive scenarios in which user queries dynamically trigger multi-source retrieval, cross-modal reasoning, and result synthesis, illustrating how compound AI systems can move beyond single database NL2SQL.

cs.AI↗

arXiv2026

Distributed Resilient Fixed-Time Control for Cooperative Output Regulation of MASs over Directed Graphs under DoS Attacks

This paper addresses the problem of fixed-time cooperative output regulation for linear multi-agent systems over directed graphs under denial-of-service attacks. A novel distributed resilient fixed-time controller is developed that comprises a distributed resilient fixed-time observer taking general directed graphs into consideration, and a distributed resilient fixed-time control law for each agent. The proposed controller neither depends on Laplacian symmetry nor requires strong connectivity and detail-balanced condition, in contrast to existing distributed resilient fixed-time controllers. Under the proposed controller, the regulated outputs converge to zero in a fixed time with its upper bound independent of the initial states of the multi-agent system. Ultimately, the efficacy of the proposed controller is demonstrated via a simulation example.

eess.SY↗

arXiv2026

Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing

Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models. While Group Relative Policy Optimization (GRPO) is widely adopted, its coarse credit assignment uniformly penalizes failed rollouts, lacking the token-level focus needed to efficiently address specific deviations. Self-Distillation Policy Optimization (SDPO) addresses this by providing denser, more targeted logit-level supervision that facilitates rapid early improvement, yet it frequently collapses during prolonged training. We trace this late-stage instability to two intrinsic flaws: self-distillation on already-correct samples introduces optimization ambiguity, and the self-teacher's signal reliability progressively degrades. To resolve these issues, we propose Sample-Routed Policy Optimization (SRPO), a unified on-policy framework that routes correct samples to GRPO's reward-aligned reinforcement and failed samples to SDPO's targeted logit-level correction. SRPO further incorporates an entropy-aware dynamic weighting mechanism to suppress high-entropy, unreliable distillation targets while emphasizing confident ones. Evaluated across five benchmarks and two model scales, SRPO achieves both the rapid early improvement of SDPO and the long-horizon stability of GRPO. It consistently surpasses the peak performance of both baselines, raising the five-benchmark average on Qwen3-8B by 3.4% over GRPO and 6.3% over SDPO, while simultaneously yielding moderate response lengths and lowering per-step compute cost by up to 17.2%.

cs.LG↗

arXiv2026

RhoMorph: Rhombus-shaped Deformable Modular Robots for Stable, Medium-Independent Reconfiguration Motion

In this paper, we present RhoMorph, a novel deformable planar lattice modular self-reconfigurable robot (MSRR) with a rhombus shaped module. Each module consists of a parallelogram skeleton with a single centrally mounted actuator that enables folding and unfolding along its diagonal. The core design philosophy is to achieve essential MSRR functionalities such as morphing, docking, and locomotion with minimal control complexity. This enables a continuous and stable reconfiguration process that is independent of the surrounding medium, allowing the system to reliably form various configurations in diverse environments. To leverage the unique kinematics of RhoMorph, we introduce morphpivoting, a novel motion primitive for reconfiguration that differs from advanced MSRR systems, and propose a strategy for its continuous execution. Finally, a series of physical experiments validate the module's stable reconfiguration ability, as well as its positional and docking accuracy.

cs.RO↗

arXiv2026

A Novel Reconfigurable Dexterous Hand Based on Triple-Symmetric Bricard Parallel Mechanism

This paper introduces a novel design for a robotic hand based on parallel mechanisms. The proposed hand uses a triple-symmetric Bricard linkage as its reconfigurable palm, enhancing adaptability to objects of varying shapes and sizes. Through topological and dimensional synthesis, the mechanism achieves a well-balanced degree of freedom and link configuration suitable for reconfigurable palm motion, balancing dexterity, stability, and load capacity. Furthermore, kinematic analysis is performed using screw theory and closed-loop constraints, and performance is evaluated based on workspace, stiffness, and motion/force transmission efficiency. Finally, a prototype is developed and tested through a series of grasping experiments, demonstrating the ability to perform stable and efficient manipulation across a wide range of objects. The results validate the effectiveness of the design in improving grasping versatility and operational precision, offering a promising solution for advanced robotic manipulation tasks.

cs.RO↗

arXiv2026

GLM-5: from Vibe Coding to Agentic Engineering

We present GLM-5, a next-generation foundation model designed to transition the paradigm of vibe coding to agentic engineering. Building upon the agentic, reasoning, and coding (ARC) capabilities of its predecessor, GLM-5 adopts DSA to significantly reduce training and inference costs while maintaining long-context fidelity. To advance model alignment and autonomy, we implement a new asynchronous reinforcement learning infrastructure that drastically improves post-training efficiency by decoupling generation from training. Furthermore, we propose novel asynchronous agent RL algorithms that further improve RL quality, enabling the model to learn from complex, long-horizon interactions more effectively. Through these innovations, GLM-5 achieves state-of-the-art performance on major open benchmarks. Most critically, GLM-5 demonstrates unprecedented capability in real-world coding tasks, surpassing previous baselines in handling end-to-end software engineering challenges. Code, models, and more information are available at https://github.com/zai-org/GLM-5.

cs.LG↗

arXiv2026

R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training

Self-play bootstraps LLM reasoning through an iterative Challenger-Solver loop: the Challenger is trained to generate questions that target the Solver's capabilities, and the Solver is optimized on the generated data to expand its reasoning skills. However, existing frameworks like R-Zero often exhibit non-sustained improvement, where early gains degrade as self-play continues. We identify a key failure mode, Diversity Illusion, where the Solver's training signals appear diverse yet collapse into recurring underlying patterns. It manifests as (1) Local Diversity Illusion, where diversity is enforced only within-batch, inducing cross-iteration mode cycling; and (2) Surface Diversity Illusion, where questions vary superficially but require near-identical reasoning skills. To mitigate them, we propose R-Diverse with two aligned innovations: Memory-Augmented Penalty (MAP), which uses a persistent memory bank to discourage recycling across iterations, and Skill-Aware Measurement (SAM), which evaluates diversity by the reasoning skills exercised rather than surface variation of questions. Across 10 math and general reasoning benchmarks, R-Diverse sustains gains over more iterations and consistently outperforms prior self-play methods. Code is available at https://github.com/Gengsheng-Li/R-Diverse.

cs.LG↗

arXiv2026

Eureka-Audio: Triggering Audio Intelligence in Compact Language Models

We present Eureka-Audio, a compact yet high-performance audio language model that achieves competitive performance against models that are 4 to 18 times larger across a broad range of audio understanding benchmarks. Despite containing only 1.7B parameters, Eureka-Audio demonstrates strong performance on automatic speech recognition (ASR), audio understanding, and dense audio captioning, matching or surpassing multiple 7B to 30B audio and omni-modal baselines. The model adopts a unified end-to-end architecture composed of a lightweight language backbone, a Whisper-based audio encoder, and a sparsely activated Mixture-of-Experts (MoE) adapter that explicitly accounts for audio heterogeneity and alleviates cross-modal optimization conflicts under limited capacity. To further enhance paralinguistic reasoning, we introduce DataFlux, a closed loop audio instruction data synthesis and verification pipeline that constructs high quality, logically consistent supervision from raw audio. Extensive evaluations across ASR, knowledge reasoning, safety, instruction following, and paralinguistic benchmarks, demonstrate that Eureka-Audio achieves an efficient balance between computational cost and performance. These results establish Eureka Audio as a strong and practical baseline for lightweight audio understanding models.

cs.SD↗

arXiv2026

DRAFT: Task Decoupled Latent Reasoning for Agent Safety

The advent of tool-using LLM agents shifts safety monitoring from output moderation to auditing long, noisy interaction trajectories, where risk-critical evidence is sparse-making standard binary supervision poorly suited for credit assignment. To address this, we propose DRAFT (Task Decoupled Latent Reasoning for Agent Safety), a latent reasoning framework that decouples safety judgment into two trainable stages: an Extractor that distills the full trajectory into a compact continuous latent draft, and a Reasoner that jointly attends to the draft and the original trajectory to predict safety. DRAFT avoids lossy explicit summarize-then-judge pipelines by performing evidence aggregation in latent space, enabling end-to-end differentiable training.Across benchmarks including ASSEBench and R-Judge, DRAFT consistently outperforms strong baselines, improving accuracy from 63.27% (LoRA) to 91.18% averaged over benchmarks, and learns more separable representations. Ablations demonstrate a clear synergy between the Extractor and the Reasoner.Overall, DRAFT suggests that continuous latent reasoning prior to readout is a practical path to robust agent safety under long-context supervision with sparse evidence.

cs.LG↗

arXiv2026

NExT-Guard: Training-Free Streaming Safeguard without Token-Level Labels

Large language models are increasingly deployed in streaming scenarios, rendering conventional post-hoc safeguards ineffective as they fail to interdict unsafe content in real-time. While streaming safeguards based on token-level supervised training could address this, they necessitate expensive annotations and suffer from severe overfitting. In this work, we challenge the paradigm that streaming safety must rely on token-level supervised training. Instead, it is an inherent capability of well-trained post-hoc safeguards, as they already encode token-level risk signals in hidden representations. Hence, we introduce NExT-Guard, a training-free framework that achieves streaming safeguards by monitoring interpretable latent features from Sparse Autoencoders (SAEs). It uses pretrained SAEs from publicly available base LLMs, enabling flexible, low-cost deployment without token-level supervision. Experimental results show that NExT-Guard outperforms both post-hoc and streaming safeguards based on supervised training, with superior robustness across models, SAE variants, and risk scenarios. These results make NExT-Guard a universal and scalable paradigm for real-time safety, accelerating the practical deployment of streaming safeguards.

cs.LG↗

arXiv2026

Imprints of quantum gravity effects on gravitational waves: a comparative study using extreme mass-ratio inspirals

Within a generally covariant Hamiltonian framework of loop quantum gravity (LQG), two black hole models parameterized by a quantum correction $ζ$ have recently been constructed. Using extreme mass-ratio inspirals (EMRIs) as high-precision probes, we investigate the imprints of this LQG deformation in the surrounding spacetime. Waveforms generated via an improved augmented analytic kludge (AAK) model in both LQG black hole backgrounds and in Schwarzschild spacetime are compared through a faithfulness analysis. This allows us to quantify the detectability of the deviation with LISA and to derive constraints on $ζ$ based on a detection threshold. We find that the first LQG black hole model produces significantly stronger signatures in EMRI signals than the second, making its quantum gravity effects more accessible to future space-borne gravitational-wave detection.

gr-qc↗

arXiv2026

Probing Quantum Gravity effects with Extreme Mass Ratio Inspirals around Rotating Hayward Black Holes

We investigate extreme mass-ratio inspirals (EMRIs) around a rotating Hayward black hole to assess the detectability of signatures arising from quantum gravity.The quantum parameter $α_0$, which encodes deviations from general relativity (GR), introduces extra correction terms in both the orbital frequency and the fluxes. Our results show that after one year of accumulated observation, these corrections induce a detectable dephasing in the EMRI waveform. Using the modified orbital evolution driven by $α_0$, we generate waveforms via the augmented analytic kludge (AAK) model implemented in the \texttt{FastEMRIWaveforms} package. Furthermore, we utilize the time-delay interferometry (TDI) to suppress the laser noise and phase fluctuations induced by spacecraft motion, and then employ the Fisher information matrix (FIM) to test the sensitivity of LISA in detecting deviations from GR. Our results demonstrate the potential of LISA to probe quantum-gravity effects through high-precision observations of EMRIs.

gr-qc↗

arXiv2026

Chaos as a Possible Probe for Scalar Hair in Horndeski Gravity

The detection of black hole scalar hair, a possible deviation from general relativity's "no-hair" theorem, requires sensitive probes beyond conventional methods. This study proposes chaotic dynamics as a novel indicator for scalar hair in Horndeski gravity. We investigate the motion of a spinning test particle in a static, spherically symmetric hairy black hole spacetime. Our results show that increasing scalar hair systematically suppresses orbital chaos, as evidenced by regularized precession, reduced Lyapunov exponents, and contracted Poincare sections. Furthermore, scalar hair enhances the correlation between the two gravitational wave polarization modes, restoring phase coherence. These findings demonstrate that chaotic observables and gravitational wave signatures can jointly serve as sensitive probes for black hole hair, offering a complementary approach to testing gravity in strong-field regimes.

gr-qc↗

arXiv2026

ERNIE 5.0 Technical Report

In this report, we introduce ERNIE 5.0, a natively autoregressive foundation model desinged for unified multimodal understanding and generation across text, image, video, and audio. All modalities are trained from scratch under a unified next-group-of-tokens prediction objective, based on an ultra-sparse mixture-of-experts (MoE) architecture with modality-agnostic expert routing. To address practical challenges in large-scale deployment under diverse resource constraints, ERNIE 5.0 adopts a novel elastic training paradigm. Within a single pre-training run, the model learns a family of sub-models with varying depths, expert capacities, and routing sparsity, enabling flexible trade-offs among performance, model size, and inference latency in memory- or time-constrained scenarios. Moreover, we systematically address the challenges of scaling reinforcement learning to unified foundation models, thereby guaranteeing efficient and stable post-training under ultra-sparse MoE architectures and diverse multimodal settings. Extensive experiments demonstrate that ERNIE 5.0 achieves strong and balanced performance across multiple modalities. To the best of our knowledge, among publicly disclosed models, ERNIE 5.0 represents the first production-scale realization of a trillion-parameter unified autoregressive model that supports both multimodal understanding and generation. To facilitate further research, we present detailed visualizations of modality-agnostic expert routing in the unified model, alongside comprehensive empirical analysis of elastic training, aiming to offer profound insights to the community.

cs.CL↗

arXiv2026

Self-Reconfiguration Planning for Deformable Quadrilateral Modular Robots

For lattice modular self-reconfigurable robots (MSRRs), maintaining stable connections during reconfiguration is crucial for physical feasibility and deployability. This letter presents a novel self-reconfiguration planning algorithm for deformable quadrilateral MSRRs that guarantees stable connection. The method first constructs feasible connect/disconnect actions using a virtual graph representation, and then organizes these actions into a valid execution sequence through a Dependence-based Reverse Tree (DRTree) that resolves interdependencies. We also prove that reconfiguration sequences satisfying motion characteristics exist for any pair of configurations with seven or more modules (excluding linear topologies). Finally, comparisons with a modified BiRRT algorithm highlight the superior efficiency and stability of our approach, while deployment on a physical robotic platform confirms its practical feasibility.

cs.RO↗

arXiv2026

RECAP: REwriting Conversations for Intent Understanding in Agentic Planning

Understanding user intent is essential for effective planning in conversational assistants, particularly those powered by large language models (LLMs) coordinating multiple agents. However, real-world dialogues are often ambiguous, underspecified, or dynamic, making intent detection a persistent challenge. Traditional classification-based approaches struggle to generalize in open-ended settings, leading to brittle interpretations and poor downstream planning. We propose RECAP (REwriting Conversations for Agent Planning), a new benchmark designed to evaluate and advance intent rewriting, reframing user-agent dialogues into concise representations of user goals. RECAP captures diverse challenges such as ambiguity, intent drift, vagueness, and mixed-goal conversations. Alongside the dataset, we introduce an LLM-based evaluator that assesses planning utility given the rewritten intent. Using RECAP, we develop a prompt-based rewriting approach that outperforms baselines, in terms of plan preference. We further demonstrate that fine-tuning two DPO-based rewriters yields additional utility gains. Our results highlight intent rewriting as a critical and tractable component for improving agentic planning in open-domain dialogue systems.

cs.CL↗

arXiv2026

CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal Distillation

Large Audio Language Models (LALMs) have garnered significant research interest. Despite being built upon text-based large language models (LLMs), LALMs frequently exhibit a degradation in knowledge and reasoning capabilities. We hypothesize that this limitation stems from the failure of current training paradigms to effectively bridge the acoustic-semantic gap within the feature representation space. To address this challenge, we propose CORD, a unified alignment framework that performs online cross-modal self-distillation. Specifically, it aligns audio-conditioned reasoning with its text-conditioned counterpart within a unified model. Leveraging the text modality as an internal teacher, CORD performs multi-granularity alignment throughout the audio rollout process. At the token level, it employs on-policy reverse KL divergence with importance-aware weighting to prioritize early and semantically critical tokens. At the sequence level, CORD introduces a judge-based global reward to optimize complete reasoning trajectories via Group Relative Policy Optimization (GRPO). Empirical results across multiple benchmarks demonstrate that CORD consistently enhances audio-conditioned reasoning and substantially bridges the audio-text performance gap with only 80k synthetic training samples, validating the efficacy and data efficiency of our on-policy, multi-level cross-modal alignment approach.

cs.SD↗

arXiv2026

MoE Adapter for Large Audio Language Models: Sparsity, Disentanglement, and Gradient-Conflict-Free

Extending the input modality of Large Language Models~(LLMs) to the audio domain is essential for achieving comprehensive multimodal perception. However, it is well-known that acoustic information is intrinsically \textit{heterogeneous}, entangling attributes such as speech, music, and environmental context. Existing research is limited to a dense, parameter-shared adapter to model these diverse patterns, which induces \textit{gradient conflict} during optimization, as parameter updates required for distinct attributes contradict each other. To address this limitation, we introduce the \textit{\textbf{MoE-Adapter}}, a sparse Mixture-of-Experts~(MoE) architecture designed to decouple acoustic information. Specifically, it employs a dynamic gating mechanism that routes audio tokens to specialized experts capturing complementary feature subspaces while retaining shared experts for global context, thereby mitigating gradient conflicts and enabling fine-grained feature learning. Comprehensive experiments show that the MoE-Adapter achieves superior performance on both audio semantic and paralinguistic tasks, consistently outperforming dense linear baselines with comparable computational costs. Furthermore, we will release the related code and models to facilitate future research.

cs.SD↗