arXiv subjects

Fei Pan

Publications and source records attributed to Fei Pan.

At least 19 recordsLinked to original sources

arXiv2026

CASH: A Capability-Aware Subsidy Harness for Advertiser Subsidy Allocation

Advertising platforms subsidize advertisers through billing discounts, and Advertiser Subsidy Allocation (ASA) chooses a subsidy level for every account to maximize total discounted revenue under a platform-wide subsidy-rate constraint. In practice, operators configure these subsidies from business rules, advertiser tiers and operating goals. Such configuration draws on rich business experience, yet as the advertiser base grows, tier-level policies can neither resolve how individual accounts respond across subsidy levels nor allocate a shared budget at the granularity of single accounts. We propose CASH, a Capability-Aware Subsidy Harness for ASA. CASH pairs a knowledge-guided large language model (LLM) with a data-driven numerical response model, learns from realized outcomes where each is locally reliable across accounts and subsidy levels, and turns this reliability into explicit capability licenses that govern source selection, agent review and budget allocation. Its Expected Policy Coverage Gain (EPCG) directs a limited feedback budget toward evidence expected to expand high-value reliable coverage, and the resulting feedback further improves the numerical model and updates capability estimates. In a one-month online experiment with CASH serving 60% of a large-scale advertising platform's traffic, CASH raises revenue per account by 15.35% and ADVV by 19.86% over Control at an essentially unchanged subsidy rate, with further gains in revenue quality, LTV and retention.

cs.IR↗

arXiv2026

RoFiGR: Coarse Routing, Fine Refinement via Level-Adaptive Distillation in Multimodal Generative Recommendation

Generative recommenders predict an item's semantic identifier (SID) one code at a time. Early codes select broad branches, so a routing error can exclude relevant items before fine-grained prediction begins. In multimodal recommendation, these coarse decisions must reflect collaborative preferences as well as item semantics. We introduce RoFiGR, a two-tree recommender that uses collaborative information in both SID construction and generation. It aligns cumulative L1-L2 code vectors with frozen collaborative item embeddings and explicitly encodes item distance and source level in the serialized history. During generation, a sequential teacher supervises legal branches. Fixed coarse-level weights maintain routing supervision, while a bounded adaptive residual allocates additional weight according to teacher-student demand. On Instruments, Arts, and Games, RoFiGR improves all five ranking metrics over the evaluated external baselines. Five-seed paired tests with Holm correction support the main NDCG@10 improvements. Comparisons with alternative collaborative supervision objectives and tokenizers support the proposed design. Matched task and decoding analyses distinguish the effects of training exposure, stream fusion, and candidate budgets.

cs.IR↗

arXiv2026

WhisperRec: Latent Reasoning for Efficient Foundation Recommendation Models

Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their adoption as backbones for foundation recommendation models (FRMs). Existing approaches typically enhance recommendation with explicit Chain-of-Thought (CoT) under the Think-then-Answer paradigm. However, generating lengthy rationales introduces substantial inference overhead, while fixed CoT templates struggle to model diverse, dynamic, and context-dependent user interests. We propose WhisperRec, an efficient latent reasoning framework for FRMs. WhisperRec compresses teacher-generated CoT into learnable latent reasoning tokens, enabling a Latent-Reason-then-Answer paradigm that performs reasoning in latent space without producing verbose rationales. This design retains decision-relevant reasoning information while avoiding the latency bottleneck of autoregressive rationale generation. Specifically, it first introduces Multi-View Adaptive CoT (MV-ACoT) to construct diverse, high-quality supervision from complementary perspectives on user interests. MV-ACoT also adapts reasoning complexity to each instance, applying lightweight analysis to clear cases and targeted multi-factor reasoning to challenging ones. Building on a pre-trained FRM, WhisperRec then employs a three-stage Latent Reasoning Alignment procedure to progressively internalize teacher CoT into latent representations. Finally, curriculum-based post-training activates latent-token reasoning for downstream recommendation while preserving standard recommendation capability. Experiments on an industrial-scale Kuaishou dataset and the public Kuaishou LLM-Rec benchmark show that WhisperRec consistently outperforms explicit-CoT methods and conventional baselines. Compared with explicit CoT Think and No-Think variants, WhisperRec improves SID@64 by 17.44% and 9.33%, respectively, and achieves over 10x higher online inference throughput.

cs.IR↗

arXiv2026

OneLatent: Latent Reasoning for Efficient Foundation Recommendation Models

Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their use as the backbone of foundation recommendation models (FRMs). Existing methods enhance recommendations through explicit Chain-of-Thought (CoT) reasoning under a Think-then-Answer paradigm. However, explicit CoT incurs substantial inference overhead by generating lengthy reasoning traces and relies on manually designed templates that struggle to capture diverse, dynamic user interests. We propose OneLatent, an efficient latent reasoning framework that compresses explicit reasoning traces into several learnable latent tokens, enabling Latent-Reason-then-Answer inference without generating verbose traces. OneLatent first introduces Multi-View Adaptive CoT (MV-ACoT), which creates diverse, high-quality teacher-generated supervision by exploring user interests from multiple perspectives and automatically adapting reasoning complexity to each instance. Building on pretrained FRMs, it then uses a three-stage latent-token alignment paradigm to progressively internalize CoT traces into learnable latent tokens. Finally, a multistage curriculum-based post-training strategy activates latent-token reasoning for downstream recommendation tasks. Experiments on an industrial-scale Kuaishou dataset and the public Kuaishou LLM-Rec benchmark show that OneLatent consistently outperforms explicit CoT-based methods and traditional baselines. Compared with the Think and No-Think variants of FRMs, OneLatent improves SID@64 by 17.44% and 9.33%, respectively, while achieving over 17x higher online inference throughput. We further develop a production serving system for scalable, real-time FRM inference. An online A/B test in Kuaishou's local-services advertising scenario shows that deploying OneLatent with this system yields an estimated 9.6% revenue lift over strong online baselines, including OneRec and OneReason.

cs.IR↗

arXiv2026

Advancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems

Sustaining industrial recommendation research requires using the results of one experiment to decide what to investigate next. We present AgentX-Model, the next generation of AgentX's model research framework, which connects proposal development and model experimentation within sandboxes defined by business inputs and prediction tasks. AgentX-Model adopts a dual-agent architecture comprising a Research Agent and a Model Agent. The Research Agent develops independently reviewed proposals from papers and experimental findings, while the Model Agent conducts multi-round investigations and returns code, measurements, and unresolved questions. Using the returned results, the Research Agent selects a starting implementation and formulates the next research question, allowing subsequent experiments to build on earlier findings. We organize this continuing research around four actions: Reproduce, Follow-up, Composition, and Diagnose. The first three actions drive routine research, while Diagnose acquires the evidence needed to choose a repair, including for issues raised by business feedback and online evaluation, such as prediction bias measured by PCOC. Across the production evaluation, 560 of 636 completed model-changing experiments recorded AUC above their business baselines. As research continued, some experiments recorded AUC above every comparable ancestor in their lineages. The five latest online A/B evaluations across different business settings reported gains including 10-15% in acquisition efficiency, 15-20% in target-segment advertising spend, and 0.3-0.8% in watch time; the watch-time model used approximately 10% fewer FLOPs and parameters. A dependency-aware historical-replay benchmark further evaluates research allocation, with initial results showing no consistent efficiency gain from more complex scheduling when agents already analyze and select concrete candidates.

cs.AI↗

arXiv2026

HubMixer: Progressive Latent Hub Mixing for Parameter-Efficient Feature Interaction in Recommendation

Learning effective feature interactions is central to industrial recommendation and advertising ranking systems. Recent token-mixing architectures simplify self-attention with lightweight mixing operators, improving hardware efficiency and enabling large-scale deployment. However, recommendation tokens are fundamentally heterogeneous: user profiles, item attributes, behavioral sequences, context features, statistical signals, and business-side features live in different semantic spaces and interact in sparse, sample-specific patterns. Directly mixing all tokens in the raw heterogeneous token space may therefore be parameter-inefficient, as the model must implicitly discover which feature groups should interact and how such interactions should be routed. In the paper, we propose HubMixer, a parameter-efficient latent hub mixing architecture for feature interaction in recommendation. Instead of directly mixing raw feature tokens, HubMixer introduces a small set of learnable latent hubs to organize feature interactions through an `induction--interaction--readout` paradigm. First, hub induction summarizes heterogeneous tokens into compact latent hubs, where latent hubs query input tokens through cross-attention. Second, hub interaction performs high-order interaction in the cleaner latent hub space. Third, token-conditioned readout lets each original token selectively read from the interacted hubs, injecting global interaction semantics while preserving token-level field identity. Extensive offline experiments on industrial recommendation tasks show that HubMixer outperforms the SOTA models. Online A/B testing in the Kuaishou short-video recruitment business further shows a statistically significant 5.48% improvement in resume submission conversion rate, and HubMixer has been fully deployed in production.

cs.IR↗

arXiv2026

ACQ: A Deployed Two-Stage Framework for Automated Creative Quota Allocation in Large-Scale Online Advertising

In digital advertising, demand-side platforms (DSPs) allow advertisers to create multiple ad creatives from a single photo for real-time bidding. While increasing the number of creatives can improve bidding opportunities, it cannot scale indefinitely, and the incremental advertising revenue typically exhibits diminishing returns as more creatives are generated. This raises a practical problem for DSPs: how to automatically determine an appropriate creative quota for each photo at scale. To address this problem, we propose Automated Creatives Quota (ACQ), a deployed two-stage framework for creative quota allocation in large-scale online advertising. In the first stage, ACQ predicts quota-conditioned expected revenue using a multi-task model built on an unbalanced binary tree, which is designed to handle the highly skewed revenue distribution across quota levels. In the second stage, ACQ formulates quota allocation under global capacity constraints as a multiple-choice knapsack problem (MCKP) and solves it with an efficient dual-based algorithm. Extensive offline experiments and online experiments on Kuaishou's advertising delivery platform demonstrate the effectiveness of ACQ, achieving a 6.20% increase in platform advertising revenue.

cs.AI↗

arXiv2026

EvoReason: Self-Evolving Reasoning Primitive-Guided On-Policy Distillation for Latent Reasoning in Generative Recommendation

Generative recommendation benefits from reasoning-enhanced inference, and latent reasoning offers an efficient paradigm by encoding intermediate reasoning processes into compact continuous representations for latency-sensitive deployment. Despite its efficiency, existing latent reasoning approaches typically rely on directly distilling raw chain-of-thought (CoT) trajectories into latent representations, assuming that textual reasoning traces provide sufficient supervision. However, recommendation reasoning trajectories contain diverse reasoning processes with redundant expressions and unstable reasoning paths, making raw CoT supervision suboptimal for learning transferable latent reasoning representations. To address this challenge, we propose EvoReason, a self-evolving latent reasoning framework that adaptively aligns explicit reasoning supervision with the student's latent reasoning space through primitive-guided on-policy distillation. First, EvoReason extracts reusable reasoning primitives from high-quality agentic recommendation trajectories, where each primitive captures an essential reasoning behavior and serves as a pseudo-tool for structured teacher reasoning. Then, based on these primitives, we equip the teacher with primitive-aware reasoning capabilities, enabling it to generate structured CoT supervision with reduced redundancy and improved consistency. Finally, during latent reasoning optimization, EvoReason introduces a self-evolving on-policy distillation mechanism, where the primitive-guided reasoning process evolves according to the student's latent reasoning outcomes. Through this closed-loop co-evolution, policy updates continuously improve latent reasoning behaviors is refined according to the resulting latent reasoning outcomes, enabling progressively better-aligned CoT supervision and more effective reasoning transfer.

cs.IR↗

arXiv2026

From Understanding to Action: Feedback-Grounded Policy Discovery for Generative Recommendation

Semantic-ID-based generative recommenders enable efficient next-item generation, but their item-level supervision mainly captures behavioral co-occurrence and local transitions. Large language models (LLMs) can complement these models by reasoning over heterogeneous interaction histories to understand the user's current demand. However, LLMs are not inherently trained with recommendation-specific outcome feedback, and linguistically plausible reasoning therefore does not necessarily lead to effective recommendation decisions. We term this mismatch the Understanding-Action Gap. Accordingly, we distinguish intent knowledge, which captures the user's current demand, from policy knowledge, which specifies the recommendation direction and rejection boundary under that demand. To bridge this gap, we propose a feedback-driven agent framework that first induces task-oriented intent and then discovers recommendation policies according to their incremental utility over an intent-only baseline. Candidate policies are evaluated and refined using outcome-derived feedback rather than linguistic plausibility. We further transfer the resulting intent and policy knowledge into two latent tokens of a lightweight Semantic-ID generator through dual-space relational distillation, enabling LLM-free online inference. Experiments on public benchmarks show consistent improvements over baselines, while large-scale online A/B tests achieve gains of 4.506% in Revenue and 4.621% in ADVV.

cs.IR↗

arXiv2026

Interpretable Representation via LLM-Driven Generative Disentanglement for Local-Life Service Recommendation

While large language models (LLMs) have advanced ID-based recommendation through Semantic ID (SID) modeling, existing SID generation frameworks largely follow a single-representation-then-quantization paradigm. This design faces two bottlenecks: semantic entanglement mixes heterogeneous attributes, such as geography, brand, and category, causing information loss during quantization, low-quality SIDs, and severe collisions; moreover, black-box representation learning provides neither explicit attribute semantics nor clear geographic or semantic meanings for SID positions. These limitations weaken both retrieval reliability and the ability to diagnose or control SID generation. We propose Interpretable Representation via LLM-Driven Generative Disentanglement for Local-Life Service Recommendation (LGRID). LGRID introduces a generative disentanglement paradigm through an Encode -> Disentangle -> Align -> Quantize pipeline. It first uses joint LLM encoding to preserve cross-attribute geographic-semantic dependencies, rather than encoding fields independently. A Structured Disentangled Block then routes hidden states into attribute-aligned slots for geographic and semantic factors. Synergistic Alignment Learning makes these slots both generatively decodable and discriminative for retrieval, while Dual-Stream Residual Quantization separately discretizes the two streams into compact SIDs with explicit attribute correspondence. This design yields interpretable SIDs with positions grounded in item attributes and local-service semantics. Experiments on Kuaishou and Foursquare show that LGRID consistently outperforms strong SID baselines, achieving up to a 5.44 percent relative AUC gain. It also achieves over 99 percent attribute-decoding accuracy for coarse geographic fields and reduces the full-SID collision rate to 39.9 percent, compared with 97.0 percent for LGSID.

cs.IR↗

arXiv2026

Should Missing Modalities Always Be Necessary to Repair for Multi-modal Sentiment Analysis?

Existing methods for multimodal sentiment analysis (MSA) under missing modalities usually follow a repair-first paradigm. We revisit this assumption and ask: \emph{should every missing modality be repaired?} A per-sample oracle analysis shows the answer is not always: full-modality input is optimal for only a small fraction of samples, and every modality subset is preferred by some samples. These results suggest that adding or repairing modalities may not always improve prediction, and that the utility of each modality is sample-dependent. Building on this finding, we propose \textbf{S}ufficiency-\textbf{I}nformed \textbf{E}vidential \textbf{V}al\textbf{vE} (\textbf{SIEVE}) that turns ``whether to repair'' into an explicit, learnable decision at the sample level. SIEVE compares a direct prediction branch with a repair branch, derives an empirical sufficiency signal from their per-sample loss gap, and routes each input through an evidential gate that jointly models sufficiency and its epistemic uncertainty. SIEVE is repair-agnostic: it operates as a plug-and-play decision on top of any explicit or implicit repair module, without modifying its internal design. Experiments on CMU-MOSI and IEMOCAP show that SIEVE consistently improves representative repair backbones across evaluated missing rates, and approaches the per-sample dual-branch achievable optimum.

cs.CL↗

arXiv2026

AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems

Recommendation algorithm iteration is moving from an artisanal, engineer-bound process toward an industrialized research loop, but this transition remains blocked by a structural execution bottleneck: the idea-to-launch cycle still depends on human engineers to generate hypotheses, modify production code, launch A/B experiments, and attribute online results. Innovation therefore scales linearly with headcount rather than compounding with evidence, compute, and accumulated experimental knowledge. We present AgentX, a production-deployed multi-agent system that fundamentally restructures this production function. AgentX operates as a self-evolving development engine: it autonomously generates, implements, evaluates, and learns from recommendation experiments at a scale and pace that no manual workflow can sustain. The system orchestrates four tightly coupled stages in a closed loop. A Brainstorm Agent synthesizes evidence from historical experiments, system architecture, data analysis, and external research into ranked, executable proposals. A Developing Agent translates each proposal into production-ready code through repository-grounded generation and multi-dimensional reliability verification. An Evaluation Agent conducts safe online rollout with guardrail-vetoed A/B judgment, converting both successes and failures into structured knowledge assets. A Harness Evolution layer (SGPO) then distills execution trajectories into semantic-gradient updates that continuously sharpen the agents themselves -- making the system not merely automated, but self-improving.

cs.AI↗

arXiv2026

OneReason Technical Report

Generative recommendation models in the OneRec family have been widely deployed in many real-world services, such as short-video, live-streaming, advertising, and e-commerce. However, these generative models can only benefit from the scaling advantage, while their reasoning ability is hard to activate, since we cannot construct meaningful Chain-of-Thought (CoT) sequences consisting of itemic tokens only. Inspired by the success of the reasoning-style ``think before answer'' paradigm in the LLM field, we conduct preliminary studies (i.e., OneRec-Think, OpenOneRec) to explore reasoning capability in generative recommendation. Nevertheless, we notice an unexpected phenomenon: the thinking mode does not show advantages over the non-thinking mode. Drawing insights from recent findings on CoT robustness in multi-modal language models, we argue that effective reasoning in recommendation rests on two factors: perception, the ability to ground itemic tokens in their underlying language semantics, and cognition, the ability to reorganize a user's behavior sequence into coherent latent interest points. We therefore propose OneReason, which includes: (1) strong itemic token perception in pre-training, (2) a three-level cognition-enhanced CoT format for recommendation tasks in SFT, and (3) a specialize-then-unify training recipe in RL to enhance the thinking ability.

cs.IR↗

arXiv2026

SinkRec: Mitigating Semantic State Sink in Long Sequence Recommendation with Memory-Conditioned Gated Delta Networks

Linear attention provides an efficient backbone for long-sequence recommendation by avoiding the quadratic cost of standard Transformers, but its compressed recurrent state can be dominated by repetitive behavior patterns. We identify this phenomenon as semantic state sink, where recurring semantics over-occupy the recurrent state and bias subsequent readouts. To mitigate semantic state sink, we propose SinkRec, a hybrid memory-transition looped architecture that decouples collaborative behavioral pattern storage from dynamic transition modeling. SinkRec externalizes recurring local patterns into a learnable conditional memory through residual vector quantization, reinjects the retrieved codes, and exposes memory key-value pairs to the attention block. It further introduces Temporal-Aware State-Relation Differential Gated DeltaNet (TDGD), which uses memory to purify recurrent writing and reading by suppressing memory-covered updates and removing memory-aligned readout responses. This design turns recurring semantics from state-competing signals into memory-retrievable patterns, allowing the recurrent state to focus on dynamic transitions and alleviating semantic state sink with linear-time efficiency. Experiments on public and industrial datasets demonstrate the effectiveness and efficiency of SinkRec.

cs.LG↗

arXiv2026

ReST: A Plug-and-Play Spatially-Constrained Representation Enhancement Framework for Local-Life Recommendation

Local-life recommendation have witnessed rapid growth, providing users with convenient access to daily essentials. However, this domain faces two key challenges: (1) spatial constraints, driven by the requirements of the local-life scenario, where items are usually shown only to users within a limited geographic area, indirectly reducing their exposure probability; and (2) long-tail sparsity, where few popular items dominate user interactions, while many high-quality long-tail items are largely overlooked due to imbalanced interaction opportunities. Existing methods typically adopt a user-centric perspective, such as modeling spatial user preferences or enhancing long-tail representations with collaborative filtering signals. However, we argue that an item-centric perspective is more suitable for this domain, focusing on enhancing long-tail items representation that align with the spatially-constrained characteristics of local lifestyle services. To tackle this issue, we propose ReST, a Plug-And-Play Spatially-Constrained Representation Enhancement Framework for Long-Tail Local-Life Recommendation. Specifically, we first introduce a Meta ID Warm-up Network, which initializes fundamental ID representations by injecting their basic attribute-level semantic information. Subsequently, we propose a novel Spatially-Constrained ID Representation Enhancement Network (SIDENet) based on contrastive learning, which incorporates two efficient strategies: a spatially-constrained hard sampling strategy and a dynamic representation alignment strategy. This design adaptively identifies weak ID representations based on their attribute-level information during training. It additionally enhances them by capturing latent item relationships within the spatially-constrained characteristics of local lifestyle services, while preserving compatibility with popular items.

cs.IR↗

arXiv2026

Geometric Knowledge-Assisted Federated Dual Knowledge Distillation Approach Towards Remote Sensing Satellite Imagery

Federated learning (FL) has recently become a promising solution for analyzing remote sensing satellite imagery (RSSI). However, the large scale and inherent data heterogeneity of images collected from multiple satellites, where the local data distribution of each satellite differs from the global one, present significant challenges to effective model training. To address this issue, we propose a Geometric Knowledge-Guided Federated Dual Knowledge Distillation (GK-FedDKD) framework for RSSI analysis. In our approach, each local client first distills a teacher encoder (TE) from multiple student encoders (SEs) trained with unlabeled augmented data. The TE is then connected with a shared classifier to form a teacher network (TN) that supervises the training of a new student network (SN). The intermediate representations of the TN are used to compute local covariance matrices, which are aggregated at the server to generate global geometric knowledge (GGK). This GGK is subsequently employed for local embedding augmentation to further guide SN training. We also design a novel loss function and a multi-prototype generation pipeline to stabilize the training process. Evaluation over multiple datasets showcases that the proposed GK-FedDKD approach is superior to the considered state-of-the-art baselines, e.g., the proposed approach with the Swin-T backbone surpasses previous SOTA approaches by an average 68.89% on the EuroSAT dataset.

cs.CV↗

arXiv2026

LBM: Hierarchical Large Auto-Bidding Model via Reasoning and Acting

The growing scale of ad auctions on online advertising platforms has intensified competition, making manual bidding impractical and necessitating auto-bidding to help advertisers achieve their economic goals. Current auto-bidding methods have evolved to use offline reinforcement learning or generative methods to optimize bidding strategies, but they can sometimes behave counterintuitively due to the black-box training manner and limited mode coverage of datasets, leading to challenges in understanding task status and generalization in dynamic ad environments. Large language models (LLMs) offer a promising solution by leveraging prior human knowledge and reasoning abilities to improve auto-bidding performance. However, directly applying LLMs to auto-bidding faces difficulties due to the need for precise actions in competitive auctions and the lack of specialized auto-bidding knowledge, which can lead to hallucinations and suboptimal decisions. To address these challenges, we propose a hierarchical Large autoBidding Model (LBM) to leverage the reasoning capabilities of LLMs for developing a superior auto-bidding strategy. This includes a high-level LBM-Think model for reasoning and a low-level LBM-Act model for action generation. Specifically, we propose a dual embedding mechanism to efficiently fuse two modalities, including language and numerical inputs, for language-guided training of the LBM-Act; then, we propose an offline reinforcement fine-tuning technique termed GQPO for mitigating the LLM-Think's hallucinations and enhancing decision-making performance without simulation or real-world rollout like previous multi-turn LLM-based methods. Experiments demonstrate the superiority of a generative backbone based on our LBM, especially in an efficient training manner and generalization ability.

cs.CL↗

arXiv2026

Hierarchical Semantic RL: Tackling the Problem of Dynamic Action Space for RL-based Recommendations

Recommender Systems (RS) are fundamental to modern online services. While most existing approaches optimize for short-term engagement, recent work has begun to explore reinforcement learning (RL) to model long-term user value. However, these efforts face significant challenges due to the vast, dynamic action spaces inherent in RS, which hinder stable policy learning. To resolve this bottleneck, we introduce Hierarchical Semantic RL (HSRL), which reframes RL-based recommendation over a fixed Semantic Action Space (SAS). HSRL encodes items as Semantic IDs (SIDs) for policy learning, and maps SIDs back to their original items via a fixed lookup during execution. To align decision-making with SID generation, the Hierarchical Policy Network (HPN) operates in a coarse-to-fine manner, employing hierarchical residual state modeling to refine each level's context from the previous level's residual, thereby reducing representation-decision mismatch. In parallel, a Multi-level Critic (MLC) provides token-level value estimates, enabling fine-grained credit assignment. Across public benchmarks and a large-scale production dataset from a leading short-video advertising platform, HSRL consistently surpasses state-of-the-art baselines. In online deployment over a 7-day A/B testing, it delivers an 18.421% ADVV lift and a 1.251% increase in Revenue, supporting HSRL as a scalable paradigm for RL-based recommendation.

cs.IR↗