arXiv subjects

Haitao Wang

Publications and source records attributed to Haitao Wang.

At least 19 recordsLinked to original sources

arXiv2026

UniPolicy: Unified Objective-Specific Policies for Generative Search Advertising

Search advertising connects user intent with commercial content and plays a critical role in platform monetization. Recent systems typically align pretrained generative models with a single business reward, such as eCPM, or use naive reward fusion for preliminary multi-objective alignment. However, an ideal search advertising system must jointly account for heterogeneous objectives, including relevance, click propensity, and commercial value, to balance user experience and business value while mitigating globally suboptimal performance caused by gradient competition. We propose UniPolicy, an objective-aware multi-policy alignment framework. UniPolicy combines objective-specific prefix tokens, sparse MoE-LoRA routing, and objective-specific residual FFNs to hierarchically decouple parameters within a shared backbone, providing differentiated parameter and policy-expression spaces for different business objectives. It further constructs pairwise preferences from multi-stage behavioral feedback, supplementing the relative preference information in exposed-but-unclicked samples and strengthening the relative advantage of clicked candidates in the generation distribution. At inference, UniPolicy supports parallel, business-customizable multi-policy beam search, flexibly allocating candidate quotas across objectives under a fixed retrieval budget. Large-scale offline experiments show that UniPolicy delivers balanced improvements across multiple metrics while preserving retrieval quality, outperforming single-objective reinforcement learning and naive reward-fusion baselines. In a 7-day online A/B test on a real search advertising system, UniPolicy improves CTR by 0.71%, RPS by 1.58%, and advertising revenue by 1.32%, while maintaining stable serving latency.

cs.CL↗

arXiv2026

CMRL: Collision-Aware and Memory-Enhanced Reinforcement Learning for UAV Navigation in Multi-Scale Obstacle Environments

In obstacle avoidance navigation of unmanned aerial vehicles (UAVs), variations in obstacle scale have received less attention than obstacle number or density. Existing methods typically extract purely geometric features from single-frame depth observations. Such representations tend to neglect small obstacles and lose spatial context under occlusions caused by large obstacles, leading to noticeable degradation in environments with multi-scale obstacles. To address this issue, we propose CMRL, a Collision-aware and Memory-enhanced Reinforcement Learning framework for UAV navigation. The collision-aware latent representation encodes risk-sensitive depth cues to preserve fine-grained obstacle structures, thereby improving sensitivity to small obstacles. The temporal memory module integrates observations across frames, mitigating partial observability caused by large-obstacle occlusions. We evaluate CMRL with multi-scale obstacles, including ultra-small and extra-large obstacle settings. Results show that CMRL outperforms state-of-the-art baselines across all scales, with success rate gains of 0.47 and 0.29 in the ultra-small and extra-large settings, respectively. More importantly, CMRL achieves reliable navigation in cluttered outdoor environments. The code is available at https://honghongdev.github.io/camerl/

cs.RO↗

arXiv2026

PACT: Phenotype-Aware Contrastive Team Representation for Multi-Phenotype Grouped Ad Hoc Teamwork

Learning to collaborate with various unfamiliar teammates poses a great challenge in the domain of multi-agent systems. Existing ad hoc teamwork methods typically drive controlled agents to collaborate with a group of teammates exhibiting a single coordination phenotype shaped by the same reward function. However, in real-world applications, controlled agents should collaborate with unfamiliar teammates of diverse coordination phenotypes among groups that have never worked together. We formalize this as the Multi-Phenotype Grouped Ad Hoc Teamwork (MPG-AHT) problem, and propose Phenotype-Aware Contrastive Team Representation (PACT) to solve this problem. PACT is empowered with phenotype-aware contrastive learning and relational reasoning to accurately distinguish coordination phenotypes and capture inter-agent interactions. Extensive experiments on multi-phenotype collaboration tasks show that PACT outperforms state-of-the-art baselines on average, achieving a mean 21.0% gain in out-of-distribution evaluation and a mean 36.5% gain in sample efficiency.

cs.MA↗

arXiv2026

Dimensional crossover and local strain induced deflection of the spin spiral state in multiferroic NiI2

Low-dimensional multiferroics hold great promise for integrated magnetoelectric devices. Spin spiral state has recently been shown to induce ferroelectricity in single-layer van der Waals (vdW) material NiI2. However, how this state evolves and can be tuned towards the two-dimensional limit remain unclear. Here, we combine spin-polarized scanning tunneling microscopy, layer-by-layer film growth, and multi-scale theoretical modeling to investigate the spin spirals in NiI2 thin films. As the film thickness increases from 1 to 7 monolayers, we observed a continuous increase of spin-spiral wavelength and a rotation of wavevector from near [110] to [1-10] direction, which evidences a dimensional crossover primarily driven by enhanced interlayer exchange energy. Moreover, we find that the film wrinkles can cause deflection of the spin spiral wavevector, which is caused by local curvature induced modification of exchange interactions. Our findings establish thickness and local strain as two tuning methods for engineering non-collinear helical magnetism and accompanied electric polarization in vdW multiferroics.

cond-mat.mes-hall↗

arXiv2026

Benchmarking and Enhancing LLMs for Rule-Intensive Review of National Standard Documents

Large language models (LLMs) increasingly support complex professional tasks, yet their capabilities in rule-intensive document review remain insufficiently evaluated. National standard documents, such as China GB/T standards, offer a representative testbed: they are lengthy, highly structured, and governed by explicit rules for scope, terminology, normative wording, and cross-section consistency. Existing benchmarks focus on domain knowledge and question answering, largely overlooking intrinsic quality review for professional documents. Such reviews rely heavily on human experts, making them costly and difficult to scale. To bridge this gap, we introduce GB/T-Bench, the first benchmark for the structured review of national standard documents. Its GB/T Review Taxonomy is a hierarchical schema covering document structure, scope alignment, normative modality, terminology consistency, and normative references, with 25 diagnosable error types. A controllable counterexample generation mechanism combines deterministic rules and constrained LLM rewriting to process 488 documents into 7,306 traceable review error instances for evaluation. We also develop a diagnosis-oriented evaluation protocol requiring exact matches on error location, review dimension, and error type, plus document-level coverage metrics. We further propose GB/T-Reviewer, a multi-agent framework that converts review knowledge into specialized skills and coordinates global inspection, targeted diagnosis, rule scanning, and result verification. Experiments with 14 mainstream LLMs reveal a substantial human-LLM gap: the strongest model achieves only 0.3280 CMCS versus 0.6640 for experts. GB/T-Reviewer raises the best CMCS to 0.5094, showing the value of structured skill coordination for rule-intensive document review. This work paves the way for trustworthy AI in standardization and other high-stakes document domains.

cs.CL↗

arXiv2026

Do Humans Bargain Differently with AI? Evidence from Alternating-Offer Games

Artificial intelligence increasingly participates in economic interactions not only as a tool, but also as an autonomous bargaining counterpart negotiating on behalf of firms, platforms, and consumers. Yet little is known about how humans respond psychologically and strategically when bargaining with such agents in dynamic settings. We study this question in a laboratory experiment using a three-stage alternating-offer bargaining game in which participants negotiate in real time with either another human or a GPT-based AI agent. We also introduce a human-beneficiary condition in which the AI agent's earnings may affect another participant's payment. Agreements are not reached earlier in human-human bargaining than in human-AI bargaining, but they are reached significantly earlier when the AI's payoff affects another participant's payoff. Human proposers offer more to human opponents than to AI agents, whereas responders become significantly more willing to accept unfair AI offers when AI earnings may benefit another human. These findings suggest that fairness and reciprocity toward AI are weaker and more conditional than toward humans, but partially remerge when AI outcomes affect real people. The results have implications for the design of AI negotiation systems and broader human-AI economic interactions.

econ.GN↗

arXiv2026

Sample Is Feature: Beyond Item-Level, Toward Sample-Level Tokens for Unified Large Recommender Models

Scaling industrial recommender models has followed two parallel paradigms: \textbf{sample information scaling} -- enriching the information content of each training sample through deeper and longer behavior sequences -- and \textbf{model capacity scaling} -- unifying sequence modeling and feature interaction within a single Transformer backbone. However, these two paradigms still face two structural limitations. Firstly, sample information scaling methods encode only a subset of each historical interaction into the sequence token, leaving the majority of the original sample context unexploited and precluding the modeling of sample-level, time-varying features. Secondly, model capacity scaling methods are inherently constrained by the structural heterogeneity between sequential and non-sequential features, preventing the model from fully realizing its representational capacity. To address these issues, we propose \textbf{SIF} (\emph{Sample Is Feature}), which encodes each historical Raw Sample directly into the sequence token -- maximally preserving sample information while simultaneously resolving the heterogeneity between sequential and non-sequential features. SIF consists of two key components. The \textbf{Sample Tokenizer} quantizes each historical Raw Sample into a Token Sample via hierarchical group-adaptive quantization (HGAQ), enabling full sample-level context to be incorporated into the sequence efficiently. The \textbf{SIF-Mixer} then performs deep feature interaction over the homogeneous sample representations via token-level and sample-level mixing, fully unleashing the model's representational capacity. Extensive experiments on a large-scale industrial dataset validate SIF's effectiveness, and we have successfully deployed SIF on an industrial food delivery platform.

cs.IR↗

arXiv2026

Not Only NTP: Extending Training Signal Coverage for Generative Recommendation

Next-Token Prediction (NTP) carries two structural training signal limitations. First, NTP optimizes for single-step prediction only, placing no supervised pressure on learning longer-range behavioral structure -- we term this \textbf{temporal locality}. Second, in multi-domain sequences, each target item embedding receives gradient updates exclusively from the immediately preceding hidden state, with no explicit gradient pathway from cross-domain context -- we term this \textbf{spatial locality}. We propose \textbf{NONTP}, extending NTP's signal coverage along both dimensions through two auxiliary objectives. \textbf{TCL (Temporal Contrastive Learning)} uses a BYOL-style EMA teacher with InfoNCE to align hidden states against a $K$-step future trajectory in representation space. \textbf{TDL (Trans-Domain Learning)} mean-pools cross-domain hidden states and predicts through the shared prediction head, opening a second gradient pathway with no additional parameters. Both are discarded at inference: zero overhead. On a four-domain Meituan industrial dataset (full ranking), NONTP achieves HR@10 +34.3\% over NTP and +18.3\% over MBGR. On the public Amazon Movie-Book-CDs benchmark, HR@10 +2.8\% and NDCG@10 +3.7\%. Online A/B tests confirm CTR +1.8\% and GMV +2.1\% (both $p < 0.01$). Ablation studies confirm each component contributes independently, with gradient conflict analyzed as a direction for future work.

cs.IR↗

arXiv2026

Shortest Path Map Equivalence Decompositions and Applications

Given a polygonal domain $P$ in the plane, the shortest path map with respect to a point $s$, denoted by $SPM(s)$, is the decomposition of $P$ into cells such that shortest paths from $s$ to all points $t$ in the same cell have the same vertex sequence. The shortest path map equivalence decomposition of $P$ is the decomposition of $P$ into cells so that $SPM(s)$ is topologically equivalent for all points $s$ in the same cell. In this paper, we prove new upper bounds on the combinatorial complexities of the $SPM$-equivalence decompositions under various settings, depending on whether $s$ and/or $t$ are restricted to the boundary of $P$. We also propose new algorithms to compute these decompositions. Further, our results lead to new solutions to several other problems, including answering two-point shortest path queries in $P$, and computing geodesic diameter and center of $P$.

cs.CG↗

arXiv2026

Next-Generation Agentic Reinforcement Learning Systems Enable Self-Evolving Agents

LLM agents are rapidly being deployed in production, including coding assistants, customer-support chatbots, and scientific research assistants, yet they remain fundamentally static in enterprise deployment. The LLM weights, system prompts, tool repertoires, and in-context harnesses are frozen at deployment time, and any improvement requires a manual loop of human-curated data collection, offline fine-tuning, modification of the agentic paradigm, and re-deployment. Recent work on self-evolving agents, such as OpenClaw for individual users, indicates that the next leap in agent capability will come from agents that continually learn from their own experience. In this paper, we argue that this vision for self-evolving agent deployment is being held back for enterprise-level large-scale agentic service not by reinforcement learning (RL) algorithms but by agentic online RL systems. Specifically, current agentic RL systems and the surrounding observability software stack are inadequate along three essential aspects: (i) there is no standardized agent trajectory data protocol capable of carrying RL learning signals at step granularity across heterogeneous agent paradigms; (ii) there is no enterprise-grade comprehensive data proxy that converts real workloads into governed learning substrates; and (iii) there is no unified agent evolution control plane that automatically decides, based on trajectory statistics, when to update policy weights or evolve the in-context harness. The next generation of agentic RL systems must be co-designed around these three pillars, and we sketch concrete architectures, case studies, and counter-arguments. We instantiate one branch through AReaL2.0, reorganizing existing RL infrastructure into an agent-oriented online RL loop for policy weight updates from deployed workloads.

cs.DC↗

arXiv2026

Kinetically Controlled Condensation Boundary Governing Indium Incorporation in InGaN Metal Organic Vapor Phase Epitaxy

We combine in situ synchrotron X-ray crystal truncation rod measurements with a binary Burton-Cabrera-Frank model to quantify indium incorporation during InGaN growth by metal-organic vapor phase epitaxy (MOVPE) on GaN(0001). By distinguishing In adatoms from condensed droplets and incorporating coupled Ga-In incorporation kinetics, the model captures the intrinsically nonlinear dependence of indium composition on precursor flux and growth temperature. The critical In coverage corresponding to the maximum attainable In composition at a given temperature is determined by a kinetic balance between In adatom supply and incorporation capacity, defining a kinetically controlled condensation boundary that shifts with temperature and Ga flux. The model quantitatively predicts this boundary, in agreement with independent measurements, and provides a predictive framework for optimizing high-In-content InGaN growth while avoiding droplet formation.

cond-mat.mtrl-sci↗

arXiv2026

DynamicPO: Dynamic Preference Optimization for Recommendation

In large language model (LLM)-based recommendation systems, direct preference optimization (DPO) effectively aligns recommendations with user preferences, requiring multi-negative objective functions to leverage abundant implicit-feedback negatives and sharpen preference boundaries. However, our empirical analyses reveal a counterintuitive phenomenon, preference optimization collapse, where increasing the number of negative samples can lead to performance degradation despite a continuously decreasing training loss. We further theoretically demonstrate that this collapse arises from gradient suppression, caused by the dominance of easily discriminable negatives over boundary-critical negatives that truly define user preference boundaries. As a result, boundary-relevant signals are under-optimized, weakening the model's decision boundary. Motivated by these observations, we propose DynamicPO (Dynamic Preference Optimization), a lightweight and plug-and-play framework comprising two adaptive mechanisms: Dynamic Boundary Negative Selection, which identifies and prioritizes informative negatives near the model's decision boundary, and Dual-Margin Dynamic beta Adjustment, which calibrates optimization strength per sample according to boundary ambiguity. Extensive experiments on three public datasets show that DynamicPO effectively prevents optimization collapse and improves recommendation accuracy on multi-negative preference optimization methods, with negligible computational overhead. Our code and datasets are available at https://github.com/xingyuHuxingyu/DynamicPO.

cs.IR↗

arXiv2026

Long-time Behaviour of DLRA for SDEs

We study dynamical orthogonal (DO) approximations of stochastic differential equations and investigate their long-time behaviour. The DO formulation represents the solution by a low-rank decomposition and leads to a coupled system consisting of an evolution equation on the Stiefel manifold and a reduced stochastic process. We establish the well-posedness of the strong DO system and derive quantitative error estimates between the original stochastic differential equation and its low-rank approximation in the Wasserstein distance. Our main contribution is the analysis of invariant probability measures for the DO dynamics. Under suitable dissipativity, Lipschitz continuity, and non-degeneracy assumptions on the coefficients, we prove the existence of an invariant probability measure for the strong DO system. The proof combines uniform moment estimates, a Krylov--Bogoliubov argument for an associated frozen system, and a Kakutani-Fan-Glicksberg fixed-point theorem to recover the self-consistent dynamics. We further show that the induced low-rank process admits an invariant probability measure and discuss the structure of invariant measures through several illustrative examples. These results provide a rigorous foundation for the use of dynamical low-rank approximations in the approximation of long-time statistical properties of stochastic dynamical systems.

math.PR↗

arXiv2026

Ling and Ring 2.6 Technical Report: Efficient and Instant Agentic Intelligence at Trillion-Parameter Scale

Efficient and scalable agentic intelligence requires models that can deliver both low-latency responses and strong reasoning capabilities while remaining practical to train, serve, and deploy. In this report, we present Ling-2.6 and Ring-2.6, a family of models designed to address this challenge at scale. Ling-2.6 is optimized for instant response generation and high capability per output token, whereas Ring-2.6 is tailored for deeper reasoning and more advanced agentic workflows. Instead of training from scratch, we upgrade the Ling-2.0 base model through architectural migration pre-training and large-scale post-training. This upgrade is guided by a unified co-design of model architecture, optimization objectives, serving systems, and agent training environments, enabling improvements in both model capability and deployment efficiency. At the architectural level, we introduce a hybrid linear attention design that integrates Lightning Attention with MLA, improving the efficiency of long-context training and decoding. To further enhance token efficiency, we optimize capability per output token through Evolutionary Chain-of-Thought, Linguistic Unit Policy Optimization, bidirectional preference alignment, and shortest-correct-response distillation. For agentic capabilities, we propose KPop, a reinforcement learning framework designed to support stable training of Ring-2.6-1T on large-scale environment-grounded data. KPop improves training efficiency through asynchronous scheduling across coding, search, tool use, and workflow execution, enabling scalable learning from complex agent-environment interactions. Together, Ling-2.6 and Ring-2.6 provide a practical pathway toward efficient, scalable, and open agentic systems. We open-source all checkpoints in the 2.6 family to support further research and development in practical agentic intelligence.

cs.CL↗

arXiv2026

Distilling LLM Reasoning into an Interpretable Policy Tree for Human-AI Collaboration

Constructing efficient and reliable policies to assist humans is indispensable for human-AI collaboration. Existing methods mainly follow two lines of work. Most prior work relies on multi-agent reinforcement learning (MARL) to learn black-box policies, which limits interpretability and raises safety concerns. Recent methods query large language models (LLMs) at each decision step, causing slow responses and high inference costs. We propose Collaboration Policy Tree (Co-pi-tree), a closed-loop method that learns an executable policy tree consisting of a partner-behavior prediction tree and an agent-action selection tree. Co-pi-tree constructs a policy by distilling LLM reasoning into policy tree code. It then evaluates the policy through partner interaction, obtains feedback, and uses natural language to summarize the interaction feedback to improve problematic branches. Experiments in Overcooked-AI show that Co-pi-tree improves average reward by 35.4% over the baseline average, while reducing the number of LLM queries by 77.7% and test-time latency by 97.1%. Project page: https://beiwenzhang.github.io/Co-pi-tree/

cs.AI↗

arXiv2026

SpectraFlow: Unifying Structural Pretraining and Frequency Adaptation for Medical Image Segmentation

Medical image segmentation remains challenging in low-data regimes, where scarce annotations often yield poor generalization and ambiguous boundaries with missing fine structures. Recent self-supervised pretraining has improved transferability, but it often exhibits a texture bias. In contrast, accurate segmentation is inherently geometry-aware and depends on both topological consistency and precise boundary preservation. To address this problem, we propose a two-stage framework that couples structure-aware encoder pretraining with boundary-oriented decoding. In Stage-1, we aim to learn structure-aware representations for downstream segmentation in low-data regimes. To this end, we propose Mixed-Domain MeanFlow Pretraining, which aligns images and binary masks in a shared latent space through latent transport regression, where masks act as conditional structural guidance rather than prediction targets, making the pretraining task-agnostic. To further improve training stability under scarce supervision, we incorporate a lightweight Dispersive Loss to prevent representation collapse. In Stage-2, we fine-tune the pretrained encoder with a lightweight decoder that combines Direct Attentional Fusion for adaptive cross-scale gating and Frequency-Directional Dynamic Convolution for high-frequency boundary refinement under appearance variation. Experiments on ISIC-2016, Kvasir-SEG, and GlaS demonstrate consistent gains over state-of-the-art methods, with improved robustness in low-data settings and sharper boundary delineation.

cs.CV↗

arXiv2026

Med-DisSeg: Dispersion-Driven Representation Learning for Fine-Grained Medical Image Segmentation

Accurate medical image segmentation is fundamental to precision medicine, yet robust delineation remains challenging under heterogeneous appearances, ambiguous boundaries, and large anatomical variability. Similar intensity and texture patterns between targets and surrounding tissues often lead to blurred activations and unreliable separation. We attribute these failures to representation collapse during encoding and insufficient fine grained multi scale decoding. To address these issues, we propose Med DisSeg, a dispersion driven medical image segmentation framework that jointly improves representation learning and anatomical delineation. Med DisSeg combines a lightweight Dispersive Loss with adaptive attention for fine grained structure segmentation. The Dispersive Loss enlarges inter sample margins by treating in batch hidden representations as negative pairs, producing well dispersed and boundary aware embeddings with negligible overhead. Based on these enhanced representations, the encoder strengthens structure sensitive responses, while the decoder performs adaptive multi scale calibration to preserve complementary local texture and global shape information. Extensive experiments on five datasets spanning three imaging modalities demonstrate consistent state of the art performance. Moreover, Med DisSeg achieves competitive results on multi organ CT segmentation, supporting its robustness and cross task applicability.

cs.CV↗

arXiv2026

CoFlow: Coordinated Few-Step Flow for Offline Multi-Agent Decision Making

Generative models have emerged as a promising paradigm for offline multi-agent reinforcement learning (MARL), but existing approaches require many iterative sampling steps. Recent few-step acceleration methods either distill a joint teacher into independent students or apply averaged velocity fields independently to each agent. Unfortunately, these few-step approaches hurt inter-agent coordination. We show that the efficiency-coordination trade-off is not inherent: single-pass multi-agent generation can preserve coordination when the velocity field is natively joint-coupled. We propose Coordinated few-step Flow (CoFlow), an architecture that combines Coordinated Velocity Attention (CVA) with Adaptive Coordination Gating. A finite-difference consistency surrogate further replaces memory-prohibitive Jacobian-vector product backpropagation through the averaged velocity field with two stop-gradient forward passes. Across 60 configurations spanning MPE, MA-MuJoCo, and SMAC, CoFlow matches or surpasses Gaussian policies, value-based methods, transformer policies, diffusion models, and prior flow baselines on episodic return. Three independent coordination probes confirm that CoFlow's improvements arise from inter-agent coordination rather than per-agent capacity. A denoising-step sweep shows that single-pass inference suffices on every configuration. CoFlow reaches state-of-the-art coordination quality in 1-3 denoising steps under both centralized and decentralized execution. Project Page: https://guowei-zou.github.io/coflow/

cs.AI↗