Searcharxiv⌕ Search

arXiv subjects

Fuzhen Zhuang

Publications and source records attributed to Fuzhen Zhuang.

At least 19 recordsLinked to original sources
arXiv2026

MARS: Modality-Aligned Retrieval for Sequence Augmented CTR Prediction

Click-through rate (CTR) prediction serves as a cornerstone of recommender systems. Despite the strong performance of current CTR models based on user behavior modeling, they are still severely limited by interaction sparsity, especially in low-active user scenarios. To address this issue, data augmentation of user behavior is a promising research direction. However, existing data augmentation methods heavily rely on collaborative signals while overlooking the rich multimodal features of items, leading to insufficient modeling of low-active users. To alleviate this problem, we propose a novel framework \textbf{MARS} (\textbf{M}odality-\textbf{A}ligned \textbf{R}etrieval for \textbf{S}equence Augmented CTR Prediction). MARS utilizes a Stein kernel-based approach to align text and image features into a unified and unbiased semantic space to construct multimodal user embeddings. Subsequently, each low-active user's behavior sequence is augmented by retrieving, filtering, and concentrating the most similar behavior sequence of high-active users via multimodal user embeddings. Validated by extensive offline experiments and online A/B tests, our framework MARS consistently outperforms state-of-the-art baselines and achieves substantial growth on core business metrics within Kuaishou~\footnote{https://www.kuaishou.com/}. Consequently, MARS has been successfully deployed, serving the main traffic for hundreds of millions of users. To ensure reproducibility, we provide anonymous access to the implementation code~\footnote{https://github.com/wangshukuan/MARS}.

cs.IR↗
arXiv2026

ICEGR: An Intent-Coherent End-to-End Generative Retrieval Framework for E-commerce Search

Generative Retrieval (GR) is promising for e-commerce search, yet existing methods struggle to maintain query-intent consistency throughout the training pipeline. First, semantic ID (SID) construction based on static product information limits the ability of SIDs to encode product-intent associations. Second, although supervised fine-tuning (SFT) learns product-SID mappings across the catalog, low-exposure products still lack real query-intent supervision because query-to-SID training relies solely on online logs, resulting in poor retrieval performance for these products. Third, business-oriented preference optimization may favor popular or high-value products over those that best match the query intent, weakening query-product relevance. To address these issues, we propose ICEGR, an Intent-Coherent End-to-End Generative Retrieval Framework for E-commerce Search that integrates query intent consistently throughout the GR training pipeline. ICEGR comprises three components: (1) Intent-Aware SID Construction incorporates query-intent signals into SID construction, enabling SIDs to capture search intent beyond static product information; (2) Synthetic Query-Enhanced Unified SFT unifies multiple SFT tasks under the query-to-SID objective and augments sparse supervision from online logs with synthetic queries, providing complementary query-intent supervision for low-exposure products; and (3) Relevance-Calibrated Preference Optimization integrates query-product relevance and business signals into a margin-adaptive preference objective, preserving query intent while enabling business preference learning. Offline results show that ICEGR improves Recall@20 by 21.7% and NDCG@20 by 26.6% over the baseline. Deployed as an end-to-end generative retrieval pathway in Baidu E-commerce Search, ICEGR achieves relative improvements of 3.52% in CTR, 15.96% in order volume, and 7.53% in GMV in an A/B test.

cs.IR↗
arXiv2026

WDL-OPD: Weak-Driven On-Policy Distillation via Mixture-Constrained Co-Training

On-policy distillation (OPD) aligns a student with a teacher on trajectories sampled from the student itself, reducing the train-test state mismatch of offline distillation. The same feedback loop can nevertheless be unstable: each update changes both the policy and the states on which the next update is computed. We introduce WDL-OPD, a mixture-constrained co-training method with two trainable policies. An anchor policy generates every rollout, an auxiliary policy evaluates the same visited states, and a geometric mixture of their token distributions is matched to a frozen teacher by reverse KL. Both policies receive gradient. We show that freezing the auxiliary recovers an anchor-plus-contrast proxy target closely related to OPD$^2$ and W2S-OPD, whereas joint training creates branch-level degrees of freedom that a static delta cannot express. In recorded Qwen3 experiments at 1.7B and 4B scale, WDL-OPD produces the strongest student checkpoint in each of four scale-domain settings. It raises MATH500 accuracy from 0.630 to 0.685 at 4B and from 0.521 to 0.585 at 1.7B. In code generation, seven single-policy OPD configurations exhibit entropy growth or trajectory degradation, while co-training reaches independently re-evaluated development scores of 0.637 and 0.375. Because several comparisons differ in curriculum or initialization, these results support a stabilization hypothesis rather than a universal causal claim. We provide the exact training algorithm, failure evidence, and the controlled comparison matrix needed to test that hypothesis.

cs.LG↗
arXiv2026

UniFAR: A Unified Facet-Aware Retrieval Framework for Scientific Documents

Scientific document retrieval (SDR) plays a critical role in modern scientific research, supporting knowledge discovery and evidence-based reasoning. It has evolved along two paradigms: document--document (doc-doc) retrieval driven by inter-document contrastive learning, and question--document (q-doc) retrieval emerging from LLMs and RAG for natural-language interaction. In practice, scientific workflows rely on both paradigms, requiring retrieval of related papers given a seed document and identifying relevant documents given a user question. However, existing methods typically treat these paradigms separately, hindering their complementary strengths. To address this, we propose UniFAR, a unified facet-aware retrieval framework that jointly supports doc-doc and q-doc retrieval within a shared representation space. UniFAR introduces a multi-granularity representation and aggregation module to unify the encoding of short questions and long documents, and a facet-level modeling mechanism with learnable anchors to capture structured semantic roles and complex user intents. It further adopts a facet-aware joint training strategy that integrates doc-doc and q-doc contrastive objectives with facet-level alignment, enabling unified learning from both inter-document relations and question-oriented supervision. Experiments on three benchmark datasets under both doc-doc and q-doc settings across multiple backbone models show that UniFAR consistently outperforms strong baselines and generalizes effectively across different backbones.

cs.IR↗
arXiv2026

D2C-Routing: Dimension-to-Composition Evidence Routing for Mixed-Origin AI-Generated Text Detection

AI-generated text detection is commonly framed as a binary document-level judgment about whether a text is human-written or machine-generated. This framing breaks down for mixed-origin writing, where content origin and expression origin may differ. We cast mixed-origin detection as dimension-to-composition source attribution, inferring content origin and expression origin before composing them into four collaboration types. We propose Dimension-to-Composition Routing (D2C-Routing), which routes content-side and expression-side evidence to supervised dimension heads before a learned gated composition layer predicts the final label. On MixD2C, a reconstructed split derived from the HART mixed-origin benchmark, our disclosed D2C-Routing-based detector system reaches 0.8603 four-way Avg TPR@1%FPR, 6.5 points above the same-split RACE-local rerun. Core ablations support the routing design, while error analysis shows that distinguishing AI-content/human-expression from fully AI-generated text remains the hardest boundary. Code is available at https://github.com/bystander563/d2c-routing-artifact.

cs.CL↗
arXiv2026

CORE-Bench: A Comprehensive Benchmark for Code Retrieval in the Era of Agentic Coding

Code retrieval is becoming central to coding agents, but agentic coding requires more than matching a natural-language query to an isolated snippet. Given a user request, a coding agent needs to navigate a concrete repository state, locate relevant files and functions, gather supporting context, and filter similar in-repository distractors. Existing code retrieval benchmarks mainly evaluate docstring-to-function or snippet-level matching, thereby missing this requirement-driven repository search problem. To address this gap, we introduce CORE-Bench, a comprehensive benchmark for code retrieval in the era of agentic coding. CORE-Bench evaluates code retrieval ability at three levels: code understanding, issue-to-edit localization, and broader context retrieval. Built from curated code-search tasks and SWE-bench-series instances, CORE-Bench contains over 180K queries and 106K broader-context relevance labels. Experiments with representative embedding models show a sharp drop from traditional code search to code retrieval in agentic coding settings. Simple supervised fine-tuning of existing embedding models significantly improves performance in this setting, suggesting substantial room for further progress.

cs.IR↗
arXiv2026

Unpaired Modality-Agnostic Generative Recommendation

Generative Recommendation (GR) formulates recommendation as autoregressive generation over discrete semantic identifiers (IDs). Although recent multimodal GR methods improve semantic ID construction with visual and textual information, they typically require item-level paired observations, restricting tokenization to the intersection of modality availability. Moreover, incorporating unpaired observations is nontrivial because small representation shifts may cross quantization boundaries and produce incompatible identifier sequences. To address this challenge, we propose \textbf{Unpair}ed Modality-Agnostic \textbf{G}enerative \textbf{R}ecommendation (UnpairGR), which learns a unified semantic-ID space from paired, image-only, and text-only observations. UnpairGR confines modality-specific processing to lightweight input projections while sharing the subsequent Transformer and residual codebooks across all observation conditions. Paired observations establish a reliability-guided cross-modal consensus, whereas unimodal observations directly refine the same representations and codes. The learned tokenizer is then fixed to provide stationary targets for a single autoregressive recommender, without feature imputation, modality-specific codebooks, or fallback mappings. Extensive experiments on three benchmark datasets demonstrate that UnpairGR consistently improves recommendation performance under both fully observed and incomplete-observation settings.

cs.IR↗
arXiv2026

Requirement--Evidence Alignment for Compositional E-Commerce Queries

Compositional e-commerce queries express multiple requirements that must hold jointly, yet existing rerankers collapse these constraints into aggregate relevance and often promote topical near misses over feasible products. In this paper, we introduce REAlign, a novel requirement-evidence-aligned reranking framework that explicitly connects typed query requirements with visible evidence. REAlign distinguishes satisfied, violated, and unsupported conditions, constructs requirement-targeted contrasts that expose failure modes, and optimizes duplicate-free partial rankings through Requirement-Aware Group-Relative Policy Optimization. Its list utility preserves relevance while incorporating requirement satisfaction, evidence support, material violations, and output validity. Experiments on two fixed-pool e-commerce benchmarks show consistent improvements over strong supervised and policy-optimization baselines under matched training budgets, with fewer violations among top-ranked candidates and larger gains at shallow ranks. Controlled ablations confirm the complementary value of requirement modeling, evidence grounding, and decomposed optimization.

cs.IR↗
arXiv2026

LASAR: Latent Adaptive Semantic Aligned Reasoning for Generative Recommendation

Large Language Models (LLMs) have demonstrated powerful reasoning capabilities through Chain-of-Thought (CoT) in various tasks, yet the inefficiency of token-by-token generation hinders real-world deployment in latency-sensitive recommender systems. Latent reasoning has emerged as an effective paradigm in LLMs, performing multi-step inference in a continuous hidden-state space to achieve stronger reasoning at lower cost. However, this paradigm remains underexplored in mainstream generative recommendation. Achieving this reveals three key challenges: (1) the gap between prior-less Semantic ID (SID) symbols and continuous latent reasoning, as SIDs lack pre-trained semantics, hindering joint optimization; (2) representation drift due to a lack of reasoning chain supervision; and (3) the suboptimality of applying a globally fixed reasoning depth. To address these, we propose LASAR (Latent Adaptive Semantic Aligned Reasoning), an SFT-then-RL framework. First, we bridge this gap via two-stage training: Stage 1 grounds SID semantics before Stage 2 introduces latent reasoning, ensuring efficient convergence. Second, we mitigate representation drift through explicit CoT semantic alignment. Step-wise bidirectional KL divergence constrains the latent reasoning trajectory using hidden-state anchors extracted from CoT text, while a Policy Head predicts per-sample reasoning depth. Third, during the GRPO-based RL phase, terminal-only KL alignment accommodates variable-length reasoning, and REINFORCE optimizes the Policy Head to dynamically allocate steps. This nearly halves the average latent step count while simultaneously improving recommendation quality. Experiments on three real-world datasets show that LASAR achieves the best overall performance across the evaluated settings. It adds limited inference latency and is roughly 20x faster than generating explicit CoT text.

cs.IR↗
arXiv2026

TextBridgeGNN: Pre-training Graph Neural Network for Cross-Domain Recommendation via Text-Guided Transfer

Graph-based recommendation has achieved great success in recent years. The classical graph recommendation model utilizes ID embedding to store essential collaborative information. However, this ID-based paradigm faces challenges in transferring to a new domain. This phenomenon primarily stems from two inherent challenges: (1) the non-transferability of ID embeddings due to isolated domain-specific ID spaces, and (2) structural incompatibility between heterogeneous interaction graphs across domains. To address these issues, we propose TextBridgeGNN, a pre-training and fine-tuning framework that can effectively transfer knowledge from a pre-trained GNN to downstream tasks. Specifically, TextBridgeGNN uses text as a semantic bridge to connect domains through multi-level graph propagation. During the pre-training stage, hierarchical GNNs are designed to learn both domain-specific and domain-global knowledge with text features, ensuring the retention of collaborative signals and the enhancement of semantics. During the fine-tuning stage, a similarity transfer mechanism initializes ID embeddings in the target domain by transferring from semantically related nodes, successfully transferring the ID embeddings and graph pattern. Experiments demonstrate that TextBridgeGNN consistently achieves strong overall performance across cross-domain, multi-domain, and training-free scenarios, without costly language model fine-tuning or real-time inference overhead.

cs.IR↗
arXiv2026

SynGR: Unleashing the Potential of Cross-Modal Synergy for Generative Recommendation

Generative Recommendation (GR) has emerged as a promising paradigm by formulating item recommendation as a sequence-to-sequence generation task over item identifiers. Recent studies have incorporated multimodal signals to provide richer token-level evidence for generation. However, existing approaches largely rely on alignment-centric fusion and underexplore synergistic information across modalities. In practice, synergistic information plays a critical role in capturing emergent item properties that cannot be inferred from any single modality alone. Such properties encode intrinsic item semantics and guide user preferences, enabling models to move beyond surface-level feature matching. To address this limitation, we propose \textbf{SynGR}, a synergistic generative recommendation framework that explicitly encourages the exploitation of cross-modal dependencies during generation. By constraining overreliance on dominant modalities, SynGR enables the model to capture emergent item semantics beyond shared or modality-specific signals. Extensive experiments across three benchmark datasets demonstrate that SynGR achieves superior performance.

cs.IR↗
arXiv2026

Counterfactual Credit Policy Optimization for Multi-Agent Collaboration

Collaborative multi-agent large language models (LLMs) can solve complex reasoning tasks by decomposing roles, but reinforcement learning for such systems is limited by credit assignment: shared terminal rewards obscure individual contributions and can encourage free-riding. We introduce two optimizer-agnostic credit assignment methods for converting joint outcomes into agent-specific learning signals. Counterfactual Credit for Policy Optimization (CCPO) estimates an agent's marginal contribution by comparing the realized joint outcome with a counterfactual outcome where that agent is removed. Self-Evaluated Credit for Policy Optimization (SEPO) uses constrained self- and peer-evaluations as a verifier-anchored credit signal while keeping the external task outcome dominant. Both operate at the reward-construction layer rather than as policy optimizers, producing role-specific rewards or advantages for GRPO, GSPO, or REINFORCE++. We instantiate these credit signals in a sequential Think--Solve setting and evaluate them on mathematical reasoning benchmarks. Results show that explicit credit assignment often improves dual-agent reasoning, especially on MATH500 and several out-of-distribution settings, while gains vary across models and datasets. Our code is available at: https://github.com/bhai114/ccpo.

cs.AI↗
arXiv2026

Beyond Matching: Category-Guided Latent Intent Reasoning for Generative Retrieval in E-Commerce

Generative retrieval offers a new paradigm for e-commerce search by mapping user queries directly to product Semantic Identifiers (SIDs). However, e-commerce queries are often short, noisy, attribute-heavy, and associated with multiple category-consistent products, creating a substantial representation gap between natural-language shopping intent and artificially constructed item SIDs. Explicit Chain-of-Thought (CoT) reasoning can help bridge this gap, but its extra generation cost is difficult to reconcile with the low-latency requirements of online e-commerce systems. To address this challenge, we propose CaLIR (Category-guided Latent Intent Reasoning), a category-guided latent intent reasoning framework for e-commerce generative retrieval. Rather than generating explicit textual rationales, CaLIR learns continuous latent intent states before SID decoding and uses product category hierarchies as a natural scaffold for coarse-to-fine intent reasoning. Specifically, we introduce hierarchical semantic reasoning to align latent states with category-level shopping intent, and query-wise reasoning enhancement to model diverse intent paths under multi-positive queries. CaLIR further combines a query-specific dynamic prefix trie, assembled from pre-indexed category-level tries, with reasoning-aware constrained decoding. Experiments on multilingual e-commerce search datasets show that CaLIR achieves a better balance between retrieval effectiveness and inference efficiency than existing methods, while also demonstrating transferability and robustness across induced hierarchies and different generative backbones.

cs.IR↗
arXiv2026

Weak-Driven Learning: How Weak Agents make Strong Agents Stronger

As post-training optimization becomes central to improving large language models, we observe a persistent saturation bottleneck: once models grow highly confident, further training yields diminishing returns. While existing methods continue to reinforce target predictions, we find that informative supervision signals remain latent in models' own historical weak states. Motivated by this observation, we propose WMSS (Weak Agents Can Make Strong Agents Stronger), a post-training paradigm that leverages weak checkpoints to guide continued optimization. By identifying recoverable learning gaps via entropy dynamics and reinforcing them through compensatory learning, WMSS enables strong agents to improve beyond conventional post-training saturation. Experiments on mathematical reasoning and code generation datasets show that agents trained with our approach achieve effective performance improvements, while incurring zero additional inference cost.

cs.AI↗
arXiv2026

Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards

Reinforcement Learning with Verifiable Rewards (RLVR) is an effective paradigm for improving the reasoning capabilities of large language models. However, existing RLVR methods utilize rollouts in an indiscriminate and short-horizon manner: responses of heterogeneous quality within each prompt are treated uniformly, and historical rollouts are discarded after a single use. This leads to noisy supervision, poor sample efficiency, and suboptimal policy updates. We address these issues by formulating rollout scheduling in RLVR as a contextual bandit problem and proposing a unified neural scheduling framework that adaptively selects high-value rollouts throughout training. Each rollout is treated as an arm whose reward is defined by the induced performance gain between consecutive optimization steps. The resulting scheduler supports both noise-aware intra-group selection and adaptive global reuse of historical rollouts within a single principled framework. We provide theoretical justification by deriving sublinear regret bounds and showing that enlarging the rollout buffer improves the achievable performance upper bound. Experiments on six mathematical reasoning benchmarks demonstrate consistent gains in performance and training efficiency across multiple RLVR optimization methods.

cs.LG↗
arXiv2026

Heterogeneous Agent Collaborative Reinforcement Learning

We introduce Heterogeneous Agent Collaborative Reinforcement Learning (HACRL), a new Reinforcement Learning from Verifiable Reward (RLVR) problem that addresses the inefficiencies of isolated multi-agent on-policy optimization. HACRL enables collaborative optimization with independent execution: heterogeneous agents share verified rollouts during training to mutually improve, while operating independently at inference time. Unlike LLM-based multi-agent reinforcement learning (MARL), HACRL does not require coordinated deployment, and unlike on-/off-policy distillation, it enables bidirectional mutual learning among heterogeneous agents rather than one-directional homogeneous teacher-to-student transfer. Building on this problem, we propose HACPO, a collaborative RL algorithm that enables principled rollout sharing to maximize sample utilization and cross-agent knowledge transfer. To mitigate capability discrepancies and policy distribution shifts, HACPO introduces four tailored mechanisms with theoretical guarantees on unbiased advantage estimation. Extensive experiments across diverse heterogeneous model combinations and reasoning benchmarks show that HACPO consistently improves all participating agents, outperforming GSPO with double rollouts by an average of 3.6% while using only half the rollout cost.

cs.LG↗
arXiv2026

Real-Time Aligned Reward Model beyond Semantics

Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet it is susceptible to reward overoptimization, in which policy models overfit to the reward model, exploit spurious reward patterns instead of faithfully capturing human intent. Prior mitigations primarily relies on surface semantic information and fails to efficiently address the misalignment between the reward model (RM) and the policy model caused by continuous policy distribution shifts. This inevitably leads to an increasing reward discrepancy, exacerbating reward overoptimization. To address these limitations, we introduce R2M (Real-Time Aligned Reward Model), a novel lightweight RLHF framework. R2M goes beyond vanilla reward models that solely depend on the semantic representations of a pretrained LLM. Instead, it leverages the evolving hidden states of the policy (namely policy feedback) to align with the real-time distribution shift of the policy during the RL process. This work points to a promising new direction for improving the performance of reward models through real-time utilization of feedback from policy models.

cs.AI↗
arXiv2026

Does Your Reasoning Model Implicitly Know When to Stop Thinking?

Recent advancements in large reasoning models (LRMs) have greatly improved their capabilities on complex reasoning tasks through Long Chains of Thought (CoTs). However, this approach often results in substantial redundancy, impairing computational efficiency and causing significant delays in real-time applications. Recent studies show that longer reasoning chains are frequently uncorrelated with correctness and can even be detrimental to accuracy. In a further in-depth analysis of this phenomenon, we surprisingly uncover and empirically verify that LRMs implicitly know the appropriate time to stop thinking, while this capability is obscured by current sampling paradigms. Motivated by this, we introduce SAGE (Self-Aware Guided Efficient Reasoning), a novel sampling paradigm that unleashes this efficient reasoning potential. Furthermore, integrating SAGE as mixed sampling into group-based reinforcement learning (SAGE-RL) enables SAGE-RL to effectively incorporate SAGE-discovered efficient reasoning patterns into standard pass@1 inference, markedly enhancing both the reasoning accuracy and efficiency of LRMs across multiple challenging mathematical benchmarks.

cs.AI↗