Searcharxiv⌕ Search

arXiv subjects

Fuzhen Zhuang

Publications and source records attributed to Fuzhen Zhuang.

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

Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection

Recent advances in large language models (LLMs) have expanded the context window to beyond 128K tokens, enabling long-document understanding and multi-source reasoning. A key challenge, however, lies in choosing between retrieval-augmented generation (RAG) and long-context (LC) strategies: RAG is efficient but constrained by retrieval quality, while LC supports global reasoning at higher cost and with position sensitivity. Existing methods such as Self-Route adopt failure-driven fallback from RAG to LC, but remain passive, inefficient, and hard to interpret. We propose Pre-Route, a proactive routing framework that performs structured reasoning before answering. Using lightweight metadata (e.g., document type, length, initial snippet), Pre-Route enables task analysis, coverage estimation, and information-need prediction, producing explainable and cost-efficient routing decisions. Our study shows three key findings: (i) LLMs possess latent routing ability that can be reliably elicited with guidelines, allowing single-sample performance to approach that of multi-sample (Best-of-N) results; (ii) linear probes reveal that structured prompts sharpen the separability of the "optimal routing dimension" in representation space; and (iii) distillation transfers this reasoning structure to smaller models for lightweight deployment. Experiments on LaRA (in-domain) and LongBench-v2 (OOD) confirm that Pre-Route outperforms Always-RAG, Always-LC, and Self-Route baselines, achieving superior overall cost-effectiveness.

cs.CL↗
arXiv2026

FedOBP: Federated Optimal Brain Personalization through Cloud-Edge Element-wise Decoupling

Federated Learning (FL) faces challenges from client data heterogeneity and resource-constrained mobile devices, which can degrade model accuracy. Personalized Federated Learning (PFL) addresses this issue by adapting shared global knowledge to local data distributions. A promising approach in PFL is model decoupling, which separates the model into global and personalized parameters, raising the key question of which parameters should be personalized to balance global knowledge sharing and local adaptation. In this paper, we propose a Federated Optimal Brain Personalization (FedOBP) algorithm with a quantile-based thresholding mechanism and introduce an element-wise importance score. This score extends Optimal Brain Damage (OBD) pruning theory by incorporating a federated approximation of the first-order derivative in the Taylor expansion to evaluate the importance of each parameter for personalization. Moreover, we move the metric computation originally performed on clients to the server side, to alleviate the burden on resource-constrained mobile devices. To the best of our knowledge, this is the first work to bridge classical saliency-based pruning theory with federated parameter decoupling, providing a rigorous theoretical justification for selecting personalized parameters based on their sensitivity to local loss landscapes. Extensive experiments demonstrate that FedOBP outperforms state-of-the-art methods across diverse datasets and heterogeneity scenarios, while requiring personalization of only a very small number of personalized parameters.

cs.LG↗
arXiv2026

Adaptive Robust Estimator for Multi-Agent Reinforcement Learning

Multi-agent collaboration has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models, yet it suffers from interaction-level ambiguity that blurs generation, critique, and revision, making credit assignment across agents difficult. Moreover, policy optimization in this setting is vulnerable to heavy-tailed and noisy rewards, which can bias advantage estimation and trigger unstable or even divergent training. To address both issues, we propose a robust multi-agent reinforcement learning framework for collaborative reasoning, consisting of two components: Dual-Agent Answer-Critique-Rewrite (DACR) and an Adaptive Robust Estimator (ARE). DACR decomposes reasoning into a structured three-stage pipeline: answer, critique, and rewrite, while enabling explicit attribution of each agent's marginal contribution to its partner's performance. ARE provides robust estimation of batch experience means during multi-agent policy optimization. Across mathematical reasoning and embodied intelligence benchmarks, even under noisy rewards, our method consistently outperforms the baseline in both homogeneous and heterogeneous settings. These results indicate stronger robustness to reward noise and more stable training dynamics, effectively preventing optimization failures caused by noisy reward signals.

cs.AI↗
arXiv2026

Learning Adaptive Distribution Alignment with Neural Characteristic Function for Graph Domain Adaptation

Graph Domain Adaptation (GDA) transfers knowledge from labeled source graphs to unlabeled target graphs but is challenged by complex, multi-faceted distributional shifts. Existing methods attempt to reduce distributional shifts by aligning manually selected graph elements (e.g., node attributes or structural statistics), which typically require manually designed graph filters to extract relevant features before alignment. However, such approaches are inflexible: they rely on scenario-specific heuristics, and struggle when dominant discrepancies vary across transfer scenarios. To address these limitations, we propose \textbf{ADAlign}, an Adaptive Distribution Alignment framework for GDA. Unlike heuristic methods, ADAlign requires no manual specification of alignment criteria. It automatically identifies the most relevant discrepancies in each transfer and aligns them jointly, capturing the interplay between attributes, structures, and their dependencies. This makes ADAlign flexible, scenario-aware, and robust to diverse and dynamically evolving shifts. To enable this adaptivity, we introduce the Neural Spectral Discrepancy (NSD), a theoretically principled parametric distance that provides a unified view of cross-graph shifts. NSD leverages neural characteristic function in the spectral domain to encode feature-structure dependencies of all orders, while a learnable frequency sampler adaptively emphasizes the most informative spectral components for each task via minimax paradigm. Extensive experiments on 10 datasets and 16 transfer tasks show that ADAlign not only outperforms state-of-the-art baselines but also achieves efficiency gains with lower memory usage and faster training.

cs.LG↗
arXiv2026

Federated Reasoning Distillation Framework with Model Learnability-Aware Data Allocation

Data allocation plays a critical role in federated large language model (LLM) and small language models (SLMs) reasoning collaboration. Nevertheless, existing data allocation methods fail to address an under-explored challenge in collaboration: bidirectional model learnability gap, where client-side SLMs cannot identify high-reward samples matching their learnability constraints for effective knowledge transfer from LLMs, while LLMs struggle to select samples contributing novel knowledge beyond their existing data. Furthermore, these collaboration frameworks face another key challenge: domain-agnostic reasoning transfer, where existing reasoning transfer methods fail to flexibly adapt to the local domain data, preventing SLMs from effectively acquiring step-by-step reasoning abilities within from general LLM. To address these challenges, we propose LaDa, a federated reasoning distillation framework with model learnability-aware data allocation. It introduces a model learnability-aware data filter that adaptively allocates high-reward samples based on the learnability gap between each SLM and LLM pair, effectively facilitating bidirectional knowledge transfer. We further design a domain adaptive reasoning distillation method that aligns joint probabilities of reasoning paths on filtered high-reward samples through contrastive distillation learning between SLM and LLM, enabling SLM to capture underlying reasoning patterns under local data distribution. LaDa operates as a plug-in module for existing collaboration frameworks, adapting knowledge transfer based on model learnability gaps.

cs.AI↗
arXiv2026

Awakening Dormant Users: Generative Recommendation with Counterfactual Functional Role Reasoning

Awakening dormant users, who remain engaged but exhibit low conversion, is a pivotal driver for incremental GMV growth in large-scale e-commerce platforms. However, existing approaches often yield suboptimal results since they typically rely on single-step estimation of an item's intrinsic value (e.g., immediate click probability). This mechanism overlooks the instrumental effect of items, where specific interactions act as triggers to shape latent intent and drive subsequent decisions along a conversion trajectory. To bridge this gap, we propose RoleGen, a novel framework that synergizes a Conversion Trajectory Reasoner with a Generative Behavioral Backbone. Specifically, the LLM-based Reasoner explicitly models the context-dependent Functional Role of items to reconstruct intent evolution. It further employs counterfactual inference to simulate diverse conversion paths, effectively mitigating interest collapse. These reasoned candidate items are integrated into the generative backbone, which is optimized via a collaborative "Reasoning-Execution-Feedback-Reflection" closed-loop strategy to ensure grounded execution. Extensive offline experiments and online A/B testing on the Kuaishou e-commerce platform demonstrate that RoleGen achieves a 6.2% gain in Recall@1 and a 7.3% increase in online order volume, confirming its effectiveness in activating the dormant user base.

cs.IR↗
arXiv2026

Learning Structure-Semantic Evolution Trajectories for Graph Domain Adaptation

Graph Domain Adaptation (GDA) aims to bridge distribution shifts between domains by transferring knowledge from well-labeled source graphs to given unlabeled target graphs. One promising recent approach addresses graph transfer by discretizing the adaptation process, typically through the construction of intermediate graphs or stepwise alignment procedures. However, such discrete strategies often fail in real-world scenarios, where graph structures evolve continuously and nonlinearly, making it difficult for fixed-step alignment to approximate the actual transformation process. To address these limitations, we propose \textbf{DiffGDA}, a \textbf{Diff}usion-based \textbf{GDA} method that models the domain adaptation process as a continuous-time generative process. We formulate the evolution from source to target graphs using stochastic differential equations (SDEs), enabling the joint modeling of structural and semantic transitions. To guide this evolution, a domain-aware network is introduced to steer the generative process toward the target domain, encouraging the diffusion trajectory to follow an optimal adaptation path. We theoretically show that the diffusion process converges to the optimal solution bridging the source and target domains in the latent space. Extensive experiments on 14 graph transfer tasks across 8 real-world datasets demonstrate DiffGDA consistently outperforms state-of-the-art baselines.

cs.LG↗
arXiv2026

Enhancing LLM-based Recommendation with Preference Hint Discovery from Knowledge Graph

LLMs have garnered substantial attention in recommendation systems. Yet they fall short of traditional recommenders when capturing complex preference patterns. Recent works have tried integrating traditional recommendation embeddings into LLMs to resolve this issue, yet a core gap persists between their continuous embedding and discrete semantic spaces. Intuitively, textual attributes derived from interactions can serve as critical preference rationales for LLMs' recommendation logic. However, directly inputting such attribute knowledge presents two core challenges: (1) Deficiency of sparse interactions in reflecting preference hints for unseen items; (2) Substantial noise introduction from treating all attributes as hints. To this end, we propose a preference hint discovery model based on the interaction-integrated knowledge graph, enhancing LLM-based recommendation. It utilizes traditional recommendation principles to selectively extract crucial attributes as hints. Specifically, we design a collaborative preference hint extraction schema, which utilizes semantic knowledge from similar users' explicit interactions as hints for unseen items. Furthermore, we develop an instance-wise dual-attention mechanism to quantify the preference credibility of candidate attributes, identifying hints specific to each unseen item. Using these item- and user-based hints, we adopt a flattened hint organization method to shorten input length and feed the textual hint information to the LLM for commonsense reasoning. Extensive experiments on both pair-wise and list-wise recommendation tasks verify the effectiveness of our proposed framework, indicating an average relative improvement of over 3.02% against baselines.

cs.IR↗
arXiv2026

Your Group-Relative Advantage Is Biased

Reinforcement Learning from Verifier Rewards (RLVR) has emerged as a widely used approach for post-training large language models on reasoning tasks, with group-based methods such as GRPO and its variants gaining broad adoption. These methods rely on group-relative advantage estimation to avoid learned critics, yet its theoretical properties remain poorly understood. In this work, we uncover a fundamental issue of group-based RL: the group-relative advantage estimator is inherently biased relative to the true (expected) advantage. We provide the first theoretical analysis showing that it systematically underestimates advantages for hard prompts and overestimates them for easy prompts, leading to imbalanced exploration and exploitation. To address this issue, we propose History-Aware Adaptive Difficulty Weighting (HA-DW), an adaptive reweighting scheme that adjusts advantage estimates based on an evolving difficulty anchor and training dynamics. Both theoretical analysis and experiments on five mathematical reasoning benchmarks demonstrate that HA-DW consistently improves performance when integrated into GRPO and its variants. Our results suggest that correcting biased advantage estimation is critical for robust and efficient RLVR training.

cs.LG↗
arXiv2026

You Only Anonymize What Is Not Intent-Relevant: Suppressing Non-Intent Privacy Evidence

Anonymizing sensitive information in user text is essential for privacy, yet existing methods often apply uniform treatment across attributes, which can conflict with communicative intent and obscure necessary information. This is particularly problematic when personal attributes are integral to expressive or pragmatic goals. The central challenge lies in determining which attributes to protect, and to what extent, while preserving semantic and pragmatic functions. We propose IntentAnony, a utility-preserving anonymization approach that performs intent-conditioned exposure control. IntentAnony models pragmatic intent and constructs privacy inference evidence chains to capture how distributed cues support attribute inference. Conditioned on intent, it assigns each attribute an exposure budget and selectively suppresses non-intent inference pathways while preserving intent-relevant content, semantic structure, affective nuance, and interactional function. We evaluate IntentAnony using privacy inference success rates, text utility metrics, and human evaluation. The results show an approximately 30% improvement in the overall privacy--utility trade-off, with notably stronger usability of anonymized text compared to prior state-of-the-art methods. Our code is available at https://github.com/Nevaeh7/IntentAnony.

cs.CR↗
arXiv2025

LLMBoost: Make Large Language Models Stronger with Boosting

Ensemble learning of LLMs has emerged as a promising alternative to enhance performance, but existing approaches typically treat models as black boxes, combining the inputs or final outputs while overlooking the rich internal representations and interactions across models.In this work, we introduce LLMBoost, a novel ensemble fine-tuning framework that breaks this barrier by explicitly leveraging intermediate states of LLMs. Inspired by the boosting paradigm, LLMBoost incorporates three key innovations. First, a cross-model attention mechanism enables successor models to access and fuse hidden states from predecessors, facilitating hierarchical error correction and knowledge transfer. Second, a chain training paradigm progressively fine-tunes connected models with an error-suppression objective, ensuring that each model rectifies the mispredictions of its predecessor with minimal additional computation. Third, a near-parallel inference paradigm design pipelines hidden states across models layer by layer, achieving inference efficiency approaching single-model decoding. We further establish the theoretical foundations of LLMBoost, proving that sequential integration guarantees monotonic improvements under bounded correction assumptions. Extensive experiments on commonsense reasoning and arithmetic reasoning tasks demonstrate that LLMBoost consistently boosts accuracy while reducing inference latency.

cs.LG↗