arXiv subjects

Yuchen Li

Publications and source records attributed to Yuchen Li.

At least 73 records · Page 4Linked to original sources

arXiv2026

Towards AI Search Paradigm

In this paper, we introduce the AI Search Paradigm, a comprehensive blueprint for next-generation search systems capable of emulating human information processing and decision-making. The paradigm employs a modular architecture of four LLM-powered agents (Master, Planner, Executor and Writer) that dynamically adapt to the full spectrum of information needs, from simple factual queries to complex multi-stage reasoning tasks. These agents collaborate dynamically through coordinated workflows to evaluate query complexity, decompose problems into executable plans, and orchestrate tool usage, task execution, and content synthesis. We systematically present key methodologies for realizing this paradigm, including task planning and tool integration, execution strategies, aligned and robust retrieval-augmented generation, and efficient LLM inference, spanning both algorithmic techniques and infrastructure-level optimizations. By providing an in-depth guide to these foundational components, this work aims to inform the development of trustworthy, adaptive, and scalable AI search systems.

cs.CL↗

arXiv2026

TURA: Tool-Augmented Unified Retrieval Agent for AI Search

The advent of Large Language Models (LLMs) is transforming search engines into conversational AI search products, primarily using Retrieval-Augmented Generation (RAG) on web corpora. However, this paradigm has significant industrial limitations. Traditional RAG approaches struggle with real-time needs and structured queries that require accessing dynamically generated content like ticket availability or inventory. Limited to indexing static pages, search engines cannot perform the interactive queries needed for such time-sensitive data. Academic research has focused on optimizing RAG for static content, overlooking complex intents and the need for dynamic sources like databases and real-time APIs. To bridge this gap, we introduce TURA (Tool-Augmented Unified Retrieval Agent for AI Search), a novel three-stage framework that combines RAG with agentic tool-use to access both static content and dynamic, real-time information. TURA has three key components: an Intent-Aware Retrieval module to decompose queries and retrieve information sources encapsulated as Model Context Protocol (MCP) Servers, a DAG-based Task Planner that models task dependencies as a Directed Acyclic Graph (DAG) for optimal parallel execution, and a lightweight Distilled Agent Executor for efficient tool calling. TURA is the first architecture to systematically bridge the gap between static RAG and dynamic information sources for a world-class AI search product. Serving tens of millions of users, it leverages an agentic framework to deliver robust, real-time answers while meeting the low-latency demands of a large-scale industrial system.

cs.CL↗

arXiv2026

AdaFuse: Accelerating Dynamic Adapter Inference via Token-Level Pre-Gating and Fused Kernel Optimization

The integration of dynamic, sparse structures like Mixture-of-Experts (MoE) with parameter-efficient adapters (e.g., LoRA) is a powerful technique for enhancing Large Language Models (LLMs). However, this architectural enhancement comes at a steep cost: despite minimal increases in computational load, the inference latency often skyrockets, leading to decoding speeds slowing by over 2.5 times. Through a fine-grained performance analysis, we pinpoint the primary bottleneck not in the computation itself, but in the severe overhead from fragmented, sequential CUDA kernel launches required for conventional dynamic routing. To address this challenge, we introduce AdaFuse, a framework built on a tight co-design between the algorithm and the underlying hardware system to enable efficient dynamic adapter execution. Departing from conventional layer-wise or block-wise routing, AdaFuse employs a token-level pre-gating strategy, which makes a single, global routing decision for all adapter layers before a token is processed. This "decide-once, apply-everywhere" approach effectively staticizes the execution path for each token, creating an opportunity for holistic optimization. We capitalize on this by developing a custom CUDA kernel that performs a fused switching operation, merging the parameters of all selected LoRA adapters into the backbone model in a single, efficient pass. Experimental results on popular open-source LLMs show that AdaFuse achieves accuracy on par with state-of-the-art dynamic adapters while drastically cutting decoding latency by a factor of over 2.4x, thereby bridging the gap between model capability and inference efficiency.

cs.AI↗

arXiv2026

BYOS: Knowledge-driven Large Language Models Bring Your Own Operating System More Excellent

Operating system (OS) kernel tuning is a critical yet challenging problem for performance optimization, due to the large configuration space, complex interdependencies among configuration options, and the rapid evolution of kernel versions. Recent work has explored large language models (LLMs) for automated kernel tuning, but existing approaches often suffer from hallucinated configurations, limited interpretability, and poor robustness across workloads and kernel versions. We propose BYOS, a knowledge-driven framework that grounds LLM-based Linux kernel tuning in structured domain knowledge. BYOS incorporates three key components: (1) structured knowledge construction and mapping to bridge the semantic gap, (2) knowledge-driven configuration generation to refine the search space, and (3) continuous knowledge maintenance to adapt to kernel evolution. We evaluate BYOS on diverse workloads across multiple Linux distributions and kernel versions. Experimental results show that BYOS consistently outperforms state-of-the-art tuning baselines, achieving 7.1%-155.4% performance improvement while substantially reducing invalid configurations. These results demonstrate the effectiveness of integrating structured knowledge with LLMs for robust and scalable system optimization. The code of BYOS is available at https://github.com/LHY-24/BYOS.

cs.OS↗

arXiv2026

MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering

Retrieval-based multimodal document QA aims to identify and integrate relevant information from visually rich documents with complex multimodal structures. While retrieval-augmented generation (RAG) has shown strong performance in text-based QA, its extensions to multimodal documents remain underexplored and face significant limitations. Specifically, current approaches rely on query-agnostic document representations that overlook salient content and use static top-k evidence selection, which fails to adapt to the uncertain distribution of relevant information. To address these limitations, we propose the Multimodal Adaptive Retrieval-Augmented (MARA) framework, which introduces query-adaptive mechanisms to both retrieval and generation. MARA consists of two components: a Query-Aligned Region Encoder that builds multi-level document representations and reweights them based on query relevance to improve retrieval precision; and a Self-Reflective Evidence Controller that monitors evidence sufficiency during generation and adaptively incorporates content from lower-ranked sources using a sliding-window strategy. Experiments on six multimodal QA benchmarks demonstrate that MARA consistently improves retrieval relevance and answer quality over existing SOTA method.

cs.IR↗

arXiv2026

Efficient Thought Space Exploration Through Strategic Intervention

While large language models (LLMs) demonstrate emerging reasoning capabilities, current inference-time expansion methods incur prohibitive computational costs by exhaustive sampling. Through analyzing decoding trajectories, we observe that most next-token predictions align well with the golden output, except for a few critical tokens that lead to deviations. Inspired by this phenomenon, we propose a novel Hint-Practice Reasoning (HPR) framework that operationalizes this insight through two synergistic components: 1) a hinter (powerful LLM) that provides probabilistic guidance at critical decision points, and 2) a practitioner (efficient smaller model) that executes major reasoning steps. The framework's core innovation lies in Distributional Inconsistency Reduction (DIR), a theoretically-grounded metric that dynamically identifies intervention points by quantifying the divergence between practitioner's reasoning trajectory and hinter's expected distribution in a tree-structured probabilistic space. Through iterative tree updates guided by DIR, HPR reweights promising reasoning paths while deprioritizing low-probability branches. Experiments across arithmetic and commonsense reasoning benchmarks demonstrate HPR's state-of-the-art efficiency-accuracy tradeoffs: it achieves comparable performance to self-consistency and MCTS baselines while decoding only 1/5 tokens, and outperforms existing methods by at most 5.1% absolute accuracy while maintaining similar or lower FLOPs.

cs.AI↗

arXiv2026

DTP: A Simple yet Effective Distracting Token Pruning Framework for Vision-Language Action Models

Vision-Language Action (VLA) models have shown remarkable progress in robotic manipulation by leveraging the powerful perception abilities of Vision-Language Models (VLMs) to understand environments and directly output actions. However, by default, VLA models may overly attend to image tokens in the task-irrelevant region, which we describe as 'distracting tokens'. This behavior can disturb the model from the generation of the desired action tokens in each step, affecting the success rate of tasks. In this paper, we introduce a simple yet effective plug-and-play Distracting Token Pruning (DTP) framework, which dynamically detects and prunes these distracting image tokens. By correcting the model's visual attention patterns, we aim to improve the task success rate, as well as exploring the performance upper boundaries of the model without altering its original architecture or adding additional inputs. Experiments on the SIMPLER Benchmark (Li et al., 2024) show that our method consistently achieving relative improvements in task success rates across different types of novel VLA models, demonstrating generalizability to transformer-based VLAs. Further analysis reveals a negative correlation between the task success rate and the amount of attentions in the task-irrelevant region for all models tested, highlighting a common phenomenon of VLA models that could guide future research. We also publish our code at: https://anonymous.4open.science/r/CBD3.

cs.CV↗

arXiv2026

Agentic-R: Learning to Retrieve for Agentic Search

Agentic search has recently emerged as a powerful paradigm, where an agent interleaves multi-step reasoning with on-demand retrieval to solve complex questions. Despite its success, how to design a retriever for agentic search remains largely underexplored. Existing search agents typically rely on similarity-based retrievers, while similar passages are not always useful for final answer generation. In this paper, we propose a novel retriever training framework tailored for agentic search. Unlike retrievers designed for single-turn retrieval-augmented generation (RAG) that only rely on local passage utility, we propose to use both local query-passage relevance and global answer correctness to measure passage utility in a multi-turn agentic search. We further introduce an iterative training strategy, where the search agent and the retriever are optimized bidirectionally and iteratively. Different from RAG retrievers that are only trained once with fixed questions, our retriever is continuously improved using evolving and higher-quality queries from the agent. Extensive experiments on seven single-hop and multi-hop QA benchmarks demonstrate that our retriever, termed \ours{}, consistently outperforms strong baselines across different search agents. Our codes are available at: https://github.com/8421BCD/Agentic-R.

cs.IR↗

arXiv2026

Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models

Recent advances in synergizing large reasoning models (LRMs) with retrieval-augmented generation (RAG) have shown promising results, yet two critical challenges remain: (1) reasoning models typically operate from a single, unchallenged perspective, limiting their ability to conduct deep, self-correcting reasoning over external documents, and (2) existing training paradigms rely excessively on outcome-oriented rewards, which provide insufficient signal for shaping the complex, multi-step reasoning process. To address these issues, we propose an Reasoner-Verifier framework named Adversarial Reasoning RAG (ARR). The Reasoner and Verifier engage in reasoning on retrieved evidence and critiquing each other's logic while being guided by process-aware advantage that requires no external scoring model. This reward combines explicit observational signals with internal model uncertainty to jointly optimize reasoning fidelity and verification rigor. Experiments on multiple benchmarks demonstrate the effectiveness of our method.

cs.AI↗

arXiv2026

FlexSpec: Frozen Drafts Meet Evolving Targets in Edge-Cloud Collaborative LLM Speculative Decoding

Deploying large language models (LLMs) in mobile and edge computing environments is constrained by limited on-device resources, scarce wireless bandwidth, and frequent model evolution. Although edge-cloud collaborative inference with speculative decoding (SD) can reduce end-to-end latency by executing a lightweight draft model at the edge and verifying it with a cloud-side target model, existing frameworks fundamentally rely on tight coupling between the two models. Consequently, repeated model synchronization introduces excessive communication overhead, increasing end-to-end latency, and ultimately limiting the scalability of SD in edge environments. To address these limitations, we propose FlexSpec, a communication-efficient collaborative inference framework tailored for evolving edge-cloud systems. The core design of FlexSpec is a shared-backbone architecture that allows a single and static edge-side draft model to remain compatible with a large family of evolving cloud-side target models. By decoupling edge deployment from cloud-side model updates, FlexSpec eliminates the need for edge-side retraining or repeated model downloads, substantially reducing communication and maintenance costs. Furthermore, to accommodate time-varying wireless conditions and heterogeneous device constraints, we develop a channel-aware adaptive speculation mechanism that dynamically adjusts the speculative draft length based on real-time channel state information and device energy budgets. Extensive experiments demonstrate that FlexSpec achieves superior performance compared to conventional SD approaches in terms of inference efficiency.

cs.DC↗

arXiv2026

GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

We present GLM-4.1V-Thinking, GLM-4.5V, and GLM-4.6V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the reasoning-centric training framework. We first develop a capable vision foundation model with significant potential through large-scale pre-training, which arguably sets the upper bound for the final performance. We then propose Reinforcement Learning with Curriculum Sampling (RLCS) to unlock the full potential of the model, leading to comprehensive capability enhancement across a diverse range of tasks, including STEM problem solving, video understanding, content recognition, coding, grounding, GUI-based agents, and long document interpretation. In a comprehensive evaluation across 42 public benchmarks, GLM-4.5V achieves state-of-the-art performance on nearly all tasks among open-source models of similar size, and demonstrates competitive or even superior results compared to closed-source models such as Gemini-2.5-Flash on challenging tasks including Coding and GUI Agents. Meanwhile, the smaller GLM-4.1V-9B-Thinking remains highly competitive-achieving superior results to the much larger Qwen2.5-VL-72B on 29 benchmarks. We open-source both GLM-4.1V-9B-Thinking and GLM-4.5V. We further introduce the GLM-4.6V series, open-source multimodal models with native tool use and a 128K context window. A brief overview is available at https://z.ai/blog/glm-4.6v. Code, models and more information are released at https://github.com/zai-org/GLM-V.

cs.CV↗

arXiv2025

Mortar: Evolving Mechanics for Automatic Game Design

We present Mortar, a system for autonomously evolving game mechanics for automatic game design. Game mechanics define the rules and interactions that govern gameplay, and designing them manually is a time-consuming and expert-driven process. Mortar combines a quality-diversity algorithm with a large language model to explore a diverse set of mechanics, which are evaluated by synthesising complete games that incorporate both evolved mechanics and those drawn from an archive. The mechanics are evaluated by composing complete games through a tree search procedure, where the resulting games are evaluated by their ability to preserve a skill-based ordering over players -- that is, whether stronger players consistently outperform weaker ones. We assess the mechanics based on their contribution towards the skill-based ordering score in the game. We demonstrate that Mortar produces games that appear diverse and playable, and mechanics that contribute more towards the skill-based ordering score in the game. We perform ablation studies to assess the role of each system component and a user study to evaluate the games based on human feedback.

cs.AI↗

arXiv2025

Cognitive Alignment in Personality Reasoning: Leveraging Prototype Theory for MBTI Inference

Personality recognition from text is typically cast as hard-label classification, which obscures the graded, prototype-like nature of human personality judgments. We present ProtoMBTI, a cognitively aligned framework for MBTI inference that operationalizes prototype theory within an LLM-based pipeline. First, we construct a balanced, quality-controlled corpus via LLM-guided multi-dimensional augmentation (semantic, linguistic, sentiment). Next, we LoRA-fine-tune a lightweight (<=2B) encoder to learn discriminative embeddings and to standardize a bank of personality prototypes. At inference, we retrieve top-k prototypes for a query post and perform a retrieve--reuse--revise--retain cycle: the model aggregates prototype evidence via prompt-based voting, revises when inconsistencies arise, and, upon correct prediction, retains the sample to continually enrich the prototype library. Across Kaggle and Pandora benchmarks, ProtoMBTI improves over baselines on both the four MBTI dichotomies and the full 16-type task, and exhibits robust cross-dataset generalization. Our results indicate that aligning the inference process with psychological prototype reasoning yields gains in accuracy, interpretability, and transfer for text-based personality modeling.

cs.CL↗

arXiv2025

Grounding Long-Context Reasoning with Contextual Normalization for Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) has become an essential approach for extending the reasoning and knowledge capacity of large language models (LLMs). While prior research has primarily focused on retrieval quality and prompting strategies, the influence of how the retrieved documents are framed, i.e., context format, remains underexplored. We show that seemingly superficial choices, such as delimiters or structural markers in key-value extraction, can induce substantial shifts in accuracy and stability, even when semantic content is identical. To systematically investigate this effect, we design controlled experiments that vary context density, delimiter styles, and positional placement, revealing the underlying factors that govern performance differences. Building on these insights, we introduce Contextual Normalization, a lightweight strategy that adaptively standardizes context representations before generation. Extensive experiments on both controlled and real-world RAG benchmarks across diverse settings demonstrate that the proposed strategy consistently improves robustness to order variation and strengthens long-context utilization. These findings underscore that reliable RAG depends not only on retrieving the right content, but also on how that content is presented, offering both new empirical evidence and a practical technique for better long-context reasoning.

cs.CL↗

arXiv2025

DualGazeNet: A Biologically Inspired Dual-Gaze Query Network for Salient Object Detection

Recent salient object detection (SOD) methods aim to improve performance in four key directions: semantic enhancement, boundary refinement, auxiliary task supervision, and multi-modal fusion. In pursuit of continuous gains, these approaches have evolved toward increasingly sophisticated architectures with multi-stage pipelines, specialized fusion modules, edge-guided learning, and elaborate attention mechanisms. However, this complexity paradoxically introduces feature redundancy and cross-component interference that obscure salient cues, ultimately reaching performance bottlenecks. In contrast, human vision achieves efficient salient object identification without such architectural complexity. This contrast raises a fundamental question: can we design a biologically grounded yet architecturally simple SOD framework that dispenses with most of this engineering complexity, while achieving state-of-the-art accuracy, computational efficiency, and interpretability? In this work, we answer this question affirmatively by introducing DualGazeNet, a biologically inspired pure Transformer framework that models the dual biological principles of robust representation learning and magnocellular-parvocellular dual-pathway processing with cortical attention modulation in the human visual system. Extensive experiments on five RGB SOD benchmarks show that DualGazeNet consistently surpasses 25 state-of-the-art CNN- and Transformer-based methods. On average, DualGazeNet achieves about 60\% higher inference speed and 53.4\% fewer FLOPs than four Transformer-based baselines of similar capacity (VST++, MDSAM, Sam2unet, and BiRefNet). Moreover, DualGazeNet exhibits strong cross-domain generalization, achieving leading or highly competitive performance on camouflaged and underwater SOD benchmarks without relying on additional modalities.

cs.CV↗

arXiv2025

VPN: Visual Prompt Navigation

While natural language is commonly used to guide embodied agents, the inherent ambiguity and verbosity of language often hinder the effectiveness of language-guided navigation in complex environments. To this end, we propose Visual Prompt Navigation (VPN), a novel paradigm that guides agents to navigate using only user-provided visual prompts within 2D top-view maps. This visual prompt primarily focuses on marking the visual navigation trajectory on a top-down view of a scene, offering intuitive and spatially grounded guidance without relying on language instructions. It is more friendly for non-expert users and reduces interpretive ambiguity. We build VPN tasks in both discrete and continuous navigation settings, constructing two new datasets, R2R-VP and R2R-CE-VP, by extending existing R2R and R2R-CE episodes with corresponding visual prompts. Furthermore, we introduce VPNet, a dedicated baseline network to handle the VPN tasks, with two data augmentation strategies: view-level augmentation (altering initial headings and prompt orientations) and trajectory-level augmentation (incorporating diverse trajectories from large-scale 3D scenes), to enhance navigation performance. Extensive experiments evaluate how visual prompt forms, top-view map formats, and data augmentation strategies affect the performance of visual prompt navigation. The code is available at https://github.com/farlit/VPN.

cs.CV↗

arXiv2025

Mean-Field Game of Relative Performance Portfolio for Two Populations with Poisson Common Noise

This paper studies the mean field game (MFG) and N-player game on relative performance portfolio management with two heterogeneous populations. In addition to the Brownian idiosyncratic and common noise, the first population invests in assets driven by idiosyncratic Poisson jump risk, while the second population invests in assets subject to Poisson common noise. We establish the characterization of the mean-field equilibrium (MFE) in MFG with two populations as well as the Nash equilibrium in the $N_1+N_2$-player game. Furthermore, we prove the convergence of the Nash equilibrium in the $N_1+N_2$-player game to the MFE as the number of players in two populations tends to infinity. We also discuss some impacts on MFE by the Poisson idiosyncratic risk and Poisson common noise in the context of relative performance, compensated by some numerical examples and financial implications.

math.OC↗

arXiv2025

AwareCompiler: Agentic Context-Aware Compiler Optimization via a Synergistic Knowledge-Data Driven Framework

Compiler optimization is crucial for enhancing program performance by transforming the sequence of optimization passes while maintaining correctness. Despite the promising potential of large language models (LLMs)-based agent for software optimization, automating compiler optimization remains challenging due to: (1) semantic misalignment between abstract program representations and concrete optimization passes, (2) inefficient interaction mechanisms between agents and compiler environments, and (3) reward sparsity from the extensive decision-making process within large optimization spaces. This paper introduces \textbf{AwareCompiler}, an agentic framework for compiler optimization that addresses these challenges through three key innovations: structured knowledge integration and dataset construction, knowledge-driven adaptive pass generation, and data-driven hybrid training pipeline. Experimental results on standard benchmarks demonstrate that AwareCompiler significantly outperforms existing baselines in both performance and efficiency, highlighting the effectiveness of our synergistic knowledge-data-driven approach. Our code is publicly available at https://github.com/LHY-24/AwareCompiler.

cs.PL↗