Searcharxiv⌕ Search

arXiv subjects

Ming He

Publications and source records attributed to Ming He.

At least 19 recordsLinked to original sources

Outcome-Mass Alignment: Controlling Length-Dependent Trajectory Influence in Multi-Turn LLM Agent Reinforcement Learning

To keep long interaction contexts tractable, stepwise group-relative training for multi-turn LLM agents materializes each source trajectory into multiple response rows and valid tokens. This expansion creates an outer-accounting problem distinct from within-trajectory credit assignment: row-based outcome statistics can count one episode outcome multiple times, while token-level reduction can assign unequal aggregate objective mass across trajectories. We term these effects outcome-statistics multiplicity and objective-mass imbalance. We introduce Outcome-Mass Alignment (OMA), a two-component method that makes both accounting choices explicit. Outcome Alignment computes outcome statistics over unique source trajectories, while Mass Alignment controls aggregate objective mass after within-trajectory aggregation of optimizer-native token objectives. Neither redesigns the base optimizer's credit assignment, importance ratios, or clipping. Across matched ALFWorld GRPO comparisons at two model scales, where failed trajectories typically expand much more than successful ones, OMA improves matched-horizon endpoint success by 7.0-9.4 percentage points. Ordinary WebShop exhibits weak or reversed expansion-outcome coupling and correspondingly mixed effects, whereas in a success-oriented WebShop setting, WebShop-SOL, OMA improves success nAUC from 0.399 to 0.511. Component ablations and GiGPO and GSPO comparisons further support component separability and cross-optimizer compatibility. These results show that trajectory expansion always defines an implicit weighting rule, but its practical effect depends on how expansion couples to outcomes and optimizer-native updates.

cs.CL↗

LemonHarness Technical Report

As large language model (LLM) agents are applied to longer tasks, they increasingly modify workspace state across multiple rounds of iteration. However, agents typically observe only tool outputs and log fragments, while the actual state changes occur in the file system. Without explicit workspace boundaries, state-changing operations such as file writes and temporary artifact generation may scatter changes across paths. Over time, these weakly constrained changes accumulate, making states such as modified files difficult to track. This paper presents LemonHarness, an integrated execution framework for long-horizon agents. LemonHarness establishes an explicit execution boundary by constraining state-changing operations within a clearly defined workspace and bringing model invocation, tool execution, and rule knowledge within a single controlled boundary. State-changing operations, including file writes, dependency installation, and temporary artifact creation, are executed through structured tool interfaces, with execution feedback recorded as observations available to subsequent model decisions. The system also introduces a reusable rule knowledge base, which turns recurring execution rules and acceptance criteria into runtime knowledge. LemonHarness further adds a time-aware execution mechanism that exposes elapsed and remaining budget to the model, so it can rebalance exploration, implementation, and validation effort as time pressure shifts and avoid timeouts from long waits or excessive verification. On Terminal-Bench 2.0, LemonHarness_GPT-5.3-CodeX reached 84.49% accuracy over 445 trials; pairing the same framework with the stronger GPT-5.5 backbone raised the average accuracy to 86.52% across five jobs. The results suggest that a unified runtime boundary, callable rule knowledge, and time-aware execution can improve the stability of long-horizon agent execution.

cs.AI↗

Discovering autonomous quantum error correction via deep reinforcement learning

Quantum error correction is essential for fault-tolerant quantum computing. However, standard methods relying on active measurements may introduce additional errors. Autonomous quantum error correction (AQEC) circumvents this by utilizing engineered dissipation and drives in bosonic systems, but identifying practical encoding remains challenging due to stringent Knill-Laflamme conditions. In this work, we utilize curriculum learning enabled deep reinforcement learning to discover Bosonic codes under approximate AQEC framework to resist both single-photon and double-photon losses. We present an analytical solution of solving the master equation under approximation conditions, which can significantly accelerate the training process of reinforcement learning. The agent first identifies an encoded subspace surpassing the breakeven point through rapid exploration within a constrained evolutionary time-frame, then strategically fine-tunes its policy to sustain this performance advantage over extended temporal horizons. We find that the two-phase trained agent can discover the optimal set of codewords, i.e., the Fock states $\ket{4}$ and $\ket{7}$ considering the effect of both single-photon and double-photon loss. We identify that the discovered code surpasses the breakeven threshold over a longer evolution time and achieve the state-of-art performance. We also analyze the robustness of the code against the phase damping and amplitude damping noise. Our work highlights the potential of curriculum learning enabled deep reinforcement learning in discovering the optimal quantum error correct code especially in early fault-tolerant quantum systems.

quant-ph↗

SIC3D: Style Image Conditioned Text-to-3D Gaussian Splatting Generation

Recent progress in text-to-3D object generation enables the synthesis of detailed geometry from text input by leveraging 2D diffusion models and differentiable 3D representations. However, the approaches often suffer from limited controllability and texture ambiguity due to the limitation of the text modality. To address this, we present SIC3D, a controllable image-conditioned text-to-3D generation pipeline with 3D Gaussian Splatting (3DGS). There are two stages in SIC3D. The first stage generates the 3D object content from text with a text-to-3DGS generation model. The second stage transfers style from a reference image to the 3DGS. Within this stylization stage, we introduce a novel Variational Stylized Score Distillation (VSSD) loss to effectively capture both global and local texture patterns while mitigating conflicts between geometry and appearance. A scaling regularization is further applied to prevent the emergence of artifacts and preserve the pattern from the style image. Extensive experiments demonstrate that SIC3D enhances geometric fidelity and style adherence, outperforming prior approaches in both qualitative and quantitative evaluations.

cs.CV↗

Lemon Agent Technical Report

Recent advanced LLM-powered agent systems have exhibited their remarkable capabilities in tackling complex, long-horizon tasks. Nevertheless, they still suffer from inherent limitations in resource efficiency, context management, and multimodal perception. Based on these observations, Lemon Agent is introduced, a multi-agent orchestrator-worker system built on a newly proposed AgentCortex framework, which formalizes the classic Planner-Executor-Memory paradigm through an adaptive task execution mechanism. Our system integrates a hierarchical self-adaptive scheduling mechanism that operates at both the overall orchestrator layer and workers layer. This mechanism can dynamically adjust computational intensity based on task complexity. It enables orchestrator to allocate one or more workers for parallel subtask execution, while workers can further improve operational efficiency by invoking tools concurrently. By virtue of this two-tier architecture, the system achieves synergistic balance between global task coordination and local task execution, thereby optimizing resource utilization and task processing efficiency in complex scenarios. To reduce context redundancy and increase information density during parallel steps, we adopt a three-tier progressive context management strategy. To make fuller use of historical information, we propose a self-evolving memory system, which can extract multi-dimensional valid information from all historical experiences to assist in completing similar tasks. Furthermore, we provide an enhanced MCP toolset. Empirical evaluations on authoritative benchmarks demonstrate that our Lemon Agent can achieve a state-of-the-art 91.36% overall accuracy on GAIA and secures the top position on the xbench-DeepSearch leaderboard with a score of 77+.

cs.MA↗

When Personalization Misleads: Understanding and Mitigating Hallucinations in Personalized LLMs

Personalized large language models (LLMs) adapt model behavior to individual users to enhance user satisfaction, yet personalization can inadvertently distort factual reasoning. We show that when personalized LLMs face factual queries, there exists a phenomenon where the model generates answers aligned with a user's prior history rather than the objective truth, resulting in personalization-induced hallucinations that degrade factual reliability and may propagate incorrect beliefs, due to representational entanglement between personalization and factual representations. To address this issue, we propose Factuality-Preserving Personalized Steering (FPPS), a lightweight inference-time approach that mitigates personalization-induced factual distortions while preserving personalized behavior. We further introduce PFQABench, the first benchmark designed to jointly evaluate factual and personalized question answering under personalization. Experiments across multiple LLM backbones and personalization methods show that FPPS substantially improves factual accuracy while maintaining personalized performance.

cs.CL↗

Optical diffraction neural networks assisted computational ghost imaging through dynamic scattering media

Ghost imaging leverages a single-pixel detector with no spatial resolution to acquire object echo intensity signals, which are correlated with illumination patterns to reconstruct an image. This architecture inherently mitigates scattering interference between the object and the detector but sensitive to scattering between the light source and the object. To address this challenge, we propose an optical diffraction neural networks (ODNNs) assisted ghost imaging method for imaging through dynamic scattering media. In our scheme, a set of fixed ODNNs, trained on simulated datasets, is incorporated into the experimental optical path to actively correct random distortions induced by dynamic scattering media. Experimental validation using rotating single-layer and double-layer ground glass confirms the feasibility and effectiveness of our approach. Furthermore, our scheme can also be combined with physics-prior-based reconstruction algorithms, enabling high-quality imaging under undersampled conditions. This work demonstrates a novel strategy for imaging through dynamic scattering media, which can be extended to other imaging systems.

physics.optics↗

LLaDA-Rec: Discrete Diffusion for Parallel Semantic ID Generation in Generative Recommendation

Generative recommendation represents each item as a semantic ID, i.e., a sequence of discrete tokens, and generates the next item through autoregressive decoding. While effective, existing autoregressive models face two intrinsic limitations: (1) unidirectional constraints, where causal attention restricts each token to attend only to its predecessors, hindering global semantic modeling; and (2) error accumulation, where the fixed left-to-right generation order causes prediction errors in early tokens to propagate to the predictions of subsequent token. To address these issues, we propose LLaDA-Rec, a discrete diffusion framework that reformulates recommendation as parallel semantic ID generation. By combining bidirectional attention with the adaptive generation order, the approach models inter-item and intra-item dependencies more effectively and alleviates error accumulation. Specifically, our approach comprises three key designs: (1) a parallel tokenization scheme that produces semantic IDs for bidirectional modeling, addressing the mismatch between residual quantization and bidirectional architectures; (2) two masking mechanisms at the user-history and next-item levels to capture both inter-item sequential dependencies and intra-item semantic relationships; and (3) an adapted beam search strategy for adaptive-order discrete diffusion decoding, resolving the incompatibility of standard beam search with diffusion-based generation. Experiments on three real-world datasets show that LLaDA-Rec consistently outperforms both ID-based and state-of-the-art generative recommenders, establishing discrete diffusion as a new paradigm for generative recommendation.

cs.IR↗

ReInAgent: A Context-Aware GUI Agent Enabling Human-in-the-Loop Mobile Task Navigation

Mobile GUI agents exhibit substantial potential to facilitate and automate the execution of user tasks on mobile phones. However, exist mobile GUI agents predominantly privilege autonomous operation and neglect the necessity of active user engagement during task execution. This omission undermines their adaptability to information dilemmas including ambiguous, dynamically evolving, and conflicting task scenarios, leading to execution outcomes that deviate from genuine user requirements and preferences. To address these shortcomings, we propose ReInAgent, a context-aware multi-agent framework that leverages dynamic information management to enable human-in-the-loop mobile task navigation. ReInAgent integrates three specialized agents around a shared memory module: an information-managing agent for slot-based information management and proactive interaction with the user, a decision-making agent for conflict-aware planning, and a reflecting agent for task reflection and information consistency validation. Through continuous contextual information analysis and sustained user-agent collaboration, ReInAgent overcomes the limitation of existing approaches that rely on clear and static task assumptions. Consequently, it enables more adaptive and reliable mobile task navigation in complex, real-world scenarios. Experimental results demonstrate that ReInAgent effectively resolves information dilemmas and produces outcomes that are more closely aligned with genuine user preferences. Notably, on complex tasks involving information dilemmas, ReInAgent achieves a 25% higher success rate than Mobile-Agent-v2.

cs.AI↗

ORMind: A Cognitive-Inspired End-to-End Reasoning Framework for Operations Research

Operations research (OR) is widely deployed to solve critical decision-making problems with complex objectives and constraints, impacting manufacturing, logistics, finance, and healthcare outcomes. While Large Language Models (LLMs) have shown promising results in various domains, their practical application in industry-relevant operations research (OR) problems presents significant challenges and opportunities. Preliminary industrial applications of LLMs for operations research face two critical deployment challenges: 1) Self-correction focuses on code syntax rather than mathematical accuracy, causing costly errors; 2) Complex expert selection creates unpredictable workflows that reduce transparency and increase maintenance costs, making them impractical for time-sensitive business applications. To address these business limitations, we introduce ORMind, a cognitive-inspired framework that enhances optimization through counterfactual reasoning. Our approach emulates human cognition, implementing an end-to-end workflow that systematically transforms requirements into mathematical models and executable solver code. It is currently being tested internally in Lenovo's AI Assistant, with plans to enhance optimization capabilities for both business and consumer customers. Experiments demonstrate that ORMind outperforms existing methods, achieving a 9.5\% improvement on the NL4Opt dataset and a 14.6\% improvement on the ComplexOR dataset.

cs.AI↗

Real-time imaging through dynamic scattering media enabled by fixed optical modulations

Dynamic scattering remains a significant challenge to the practical deployment of anti-scattering imaging. Existing methods, such as transmission matrix measurements, iterative wavefront shaping, and optical phase conjugation, depend on a quasi-static assumption, requiring the object and scattering medium to remain stable during a single imaging process to enable one-to-one compensation. However, image reconstruction becomes unattainable when this assumption is violated. Here, we propose a novel imaging strategy that counteracts time-dependent scattering perturbations through a fixed modulation module. This one-to-many compensation mechanism is realized via optical diffraction neural networks (ODNNs) trained on simulated datasets. For the first time, we reveal that its feasibility stems from the optical shower-curtain effect, and its effectiveness typically within 1-2 transport mean free paths. Our approach is not only immune to speckle decorrelation but also leverages it to enhance image quality. ODNNs generalize effectively to real-world scattering medium scenarios via multi-simulated scattering media learning and reconstruct images in real time with light-speed processing. We achieve 80 Hz imaging of moving objects in dynamic scattering media with decorrelation times < 1 ms, demonstrating applicability in large-field-of-view imaging and incoherent illumination scenarios. This work lays the foundation for high-speed, intelligent optical imaging, advancing practical anti-dynamic scattering techniques.

physics.optics↗

Paragon: Parameter Generation for Controllable Multi-Task Recommendation

Commercial recommender systems face the challenge that task requirements from platforms or users often change dynamically (e.g., varying preferences for accuracy or diversity). Ideally, the model should be re-trained after resetting a new objective function, adapting to these changes in task requirements. However, in practice, the high computational costs associated with retraining make this process impractical for models already deployed to online environments. This raises a new challenging problem: how to efficiently adapt the learned model to different task requirements by controlling the model parameters after deployment, without the need for retraining. To address this issue, we propose a novel controllable learning approach via \textbf{para}meter \textbf{g}eneration for c\textbf{on}trollable multi-task recommendation (\textbf{Paragon}), which allows the customization and adaptation of recommendation model parameters to new task requirements without retraining. Specifically, we first obtain the optimized model parameters through adapter tunning based on the feasible task requirements. Then, we utilize the generative model as a parameter generator, employing classifier-free guidance in conditional training to learn the distribution of optimized model parameters under various task requirements. Finally, the parameter generator is applied to effectively generate model parameters in a test-time adaptation manner given task requirements. Moreover, Paragon seamlessly integrates with various existing recommendation models to enhance their controllability. Extensive experiments on two public datasets and one commercial dataset demonstrate that Paragon can efficiently generate model parameters instead of retraining, reducing computational time by at least 94.6\%. The code is released at \href{https://github.com/bubble65/Paragon}{https://github.com/bubble65/Paragon}.

cs.IR↗

Benefit from Rich: Tackling Search Interaction Sparsity in Search Enhanced Recommendation

In modern online platforms, search and recommendation (S&R) often coexist, offering opportunities for performance improvement through search-enhanced approaches. Existing studies show that incorporating search signals boosts recommendation performance. However, the effectiveness of these methods relies heavily on rich search interactions. They primarily benefit a small subset of users with abundant search behavior, while offering limited improvements for the majority of users who exhibit only sparse search activity. To address the problem of sparse search data in search-enhanced recommendation, we face two key challenges: (1) how to learn useful search features for users with sparse search interactions, and (2) how to design effective training objectives under sparse conditions. Our idea is to leverage the features of users with rich search interactions to enhance those of users with sparse search interactions. Based on this idea, we propose GSERec, a method that utilizes message passing on the User-Code Graphs to alleviate data sparsity in Search-Enhanced Recommendation. Specifically, we utilize Large Language Models (LLMs) with vector quantization to generate discrete codes, which connect similar users and thereby construct the graph. Through message passing on this graph, embeddings of users with rich search data are propagated to enhance the embeddings of users with sparse interactions. To further ensure that the message passing captures meaningful information from truly similar users, we introduce a contrastive loss to better model user similarities. The enhanced user representations are then integrated into downstream search-enhanced recommendation models. Experiments on three real-world datasets show that GSERec consistently outperforms baselines, especially for users with sparse search behaviors.

cs.IR↗

Bridging Search and Recommendation through Latent Cross Reasoning

Search and recommendation (S&R) are fundamental components of modern online platforms, yet effectively leveraging search behaviors to improve recommendation remains a challenging problem. User search histories often contain noisy or irrelevant signals that can even degrade recommendation performance, while existing approaches typically encode S&R histories either jointly or separately without explicitly identifying which search behaviors are truly useful. Inspired by the human decision-making process, where one first identifies recommendation intent and then reasons about relevant evidence, we design a latent cross reasoning framework that first encodes user S&R histories to capture global interests and then iteratively reasons over search behaviors to extract signals beneficial for recommendation. Contrastive learning is employed to align latent reasoning states with target items, and reinforcement learning is further introduced to directly optimize ranking performance. Extensive experiments on public benchmarks demonstrate consistent improvements over strong baselines, validating the importance of reasoning in enhancing search-aware recommendation.

cs.IR↗

MoRE: A Mixture of Reflectors Framework for Large Language Model-Based Sequential Recommendation

Large language models (LLMs) have emerged as a cutting-edge approach in sequential recommendation, leveraging historical interactions to model dynamic user preferences. Current methods mainly focus on learning processed recommendation data in the form of sequence-to-sequence text. While effective, they exhibit three key limitations: 1) failing to decouple intra-user explicit features (e.g., product titles) from implicit behavioral patterns (e.g., brand loyalty) within interaction histories; 2) underutilizing cross-user collaborative filtering (CF) signals; and 3) relying on inefficient reflection update strategies. To address this, We propose MoRE (Mixture of REflectors), which introduces three perspective-aware offline reflection processes to address these gaps. This decomposition directly resolves Challenges 1 (explicit/implicit ambiguity) and 2 (CF underutilization). Furthermore, MoRE's meta-reflector employs a self-improving strategy and a dynamic selection mechanism (Challenge 3) to adapt to evolving user preferences. First, two intra-user reflectors decouple explicit and implicit patterns from a user's interaction sequence, mimicking traditional recommender systems' ability to distinguish surface-level and latent preferences. A third cross-user reflector captures CF signals by analyzing user similarity patterns from multiple users' interactions. To optimize reflection quality, MoRE's meta-reflector employs a offline self-improving strategy that evaluates reflection impacts through comparisons of presence/absence and iterative refinement of old/new versions, with a online contextual bandit mechanism dynamically selecting the optimal perspective for recommendation for each user. Code: https://github.com/E-qin/MoRE-Rec.

cs.IR↗

Optimization of Flying Ad Hoc Network Topology and Collaborative Path Planning for Multiple UAVs

Multiple unmanned aerial vehicles (UAVs) play a vital role in monitoring and data collection in wide area environments with harsh conditions. In most scenarios, issues such as real-time data retrieval and real-time UAV positioning are often disregarded, essentially neglecting the communication constraints. In this paper, we comprehensively address both the coverage of the target area and the data transmission capabilities of the flying ad hoc network (FANET). The data throughput of the network is therefore maximized by optimizing the network topology and the UAV trajectories. The resultant optimization problem is effectively solved by the proposed reinforcement learning-based trajectory planning (RL-TP) algorithm and the convex-based topology optimization (C-TOP) algorithm sequentially. The RL-TP optimizes the UAV paths while considering the constraints of FANET. The C-TOP maximizes the data throughput of the network while simultaneously constraining the neighbors and transmit powers of the UAVs, which is shown to be a convex problem that can be efficiently solved in polynomial time. Simulations and field experimental results show that the proposed optimization strategy can effectively plan the UAV trajectories and significantly improve the data throughput of the FANET over the adaptive local minimum spanning tree (A-LMST) and cyclic pruning-assisted power optimization (CPAPO) methods.

cs.MA↗

Similarity = Value? Consultation Value Assessment and Alignment for Personalized Search

Personalized search systems in e-commerce platforms increasingly involve user interactions with AI assistants, where users consult about products, usage scenarios, and more. Leveraging consultation to personalize search services is trending. Existing methods typically rely on semantic similarity to align historical consultations with current queries due to the absence of 'value' labels, but we observe that semantic similarity alone often fails to capture the true value of consultation for personalization. To address this, we propose a consultation value assessment framework that evaluates historical consultations from three novel perspectives: (1) Scenario Scope Value, (2) Posterior Action Value, and (3) Time Decay Value. Based on this, we introduce VAPS, a value-aware personalized search model that selectively incorporates high-value consultations through a consultation-user action interaction module and an explicit objective that aligns consultations with user actions. Experiments on both public and commercial datasets show that VAPS consistently outperforms baselines in both retrieval and ranking tasks.

cs.IR↗

MAPS: Motivation-Aware Personalized Search via LLM-Driven Consultation Alignment

Personalized product search aims to retrieve and rank items that match users' preferences and search intent. Despite their effectiveness, existing approaches typically assume that users' query fully captures their real motivation. However, our analysis of a real-world e-commerce platform reveals that users often engage in relevant consultations before searching, indicating they refine intents through consultations based on motivation and need. The implied motivation in consultations is a key enhancing factor for personalized search. This unexplored area comes with new challenges including aligning contextual motivations with concise queries, bridging the category-text gap, and filtering noise within sequence history. To address these, we propose a Motivation-Aware Personalized Search (MAPS) method. It embeds queries and consultations into a unified semantic space via LLMs, utilizes a Mixture of Attention Experts (MoAE) to prioritize critical semantics, and introduces dual alignment: (1) contrastive learning aligns consultations, reviews, and product features; (2) bidirectional attention integrates motivation-aware embeddings with user preferences. Extensive experiments on real and synthetic data show MAPS outperforms existing methods in both retrieval and ranking tasks.

cs.IR↗