arXiv subjects

Yuxuan Huang

Publications and source records attributed to Yuxuan Huang.

At least 19 recordsLinked to original sources

arXiv2026

Bilevel Coordinated Reflection: A Game-Theoretic Approach to Multi-Agent LLM Systems

Multi-agent LLM systems commonly use an orchestrator to decompose a task for a team of workers and then improve through textual reflection. Despite strong empirical results, these systems lack a unified account of coordination, memory improvement, and the role of external verification. We model orchestrator-worker interaction as a bilevel coordination game: under bounded coupling, the workers' local-update game is an approximate potential game whose equilibrium slack is controlled by decomposition quality. We then analyse reflection as stochastic movement over semantic memory states. For free-form reflection, we derive a finite-time upper bound, prove worst-case tightness, and give a positive lower bound under a falsifiable persistent-harm condition. We further prove an information-theoretic impossibility result: no gate that observes only the generated transcript can improve uniformly over text-indistinguishable environments, whereas an environment-grounded gate can. Motivated by this separation, we introduce Stochastic Reflective Memory Ascent (SRMA), which accepts a candidate memory only after a grounded evaluation risk strictly decreases. Under calibration and non-degenerate corrective mass, SRMA converges exactly, geometrically or polynomially; matching constructions show that both rate regimes are order-tight. We also provide confidence gating for stochastic evaluation and re-anchoring guarantees for piecewise-stationary environments. Experiments instantiate these objects with environment-grounded metrics and test the predicted coordination and drift laws. On 500 SWE-bench instances, the complete Kimi-based system resolves 72.2% versus a 70.8% public mini-SWE-agent reference. Code: https://github.com/YihangChen9/Bilevel-Coordinated-Reflection

cs.AI↗

arXiv2026

Context or Digits? Balancing Memorability and Efficiency in Virtual Reality Authentication

We present Adaptive Direction-Based Authentication (ADBA), a knowledge-based authentication method for Virtual Reality that decouples users' needs temporally by enforcing password creation based on virtual environment context while supporting both context- and digit-based entries during authentication. This design prioritizes memorability for new passwords and offers both efficient and memorable options to support users' evolving needs. We conducted a remote longitudinal study with 66 participants comparing ADBA against 6-digit PINs over 2-3 weeks. The results demonstrated that ADBA achieved superior memorability and lower perceived task load. Interestingly, no participant chose to enter via digits in the study, yet they still perceived ADBA to be highly efficiency despite longer objective entry times. ADBA also provided security benefits through randomly-generated digit representations, though some degree of password homogeneity was observed in specific virtual environments. Our findings suggest that ADBA offers solid advantages to the traditional PINs, and successfully addresses the tradeoffs between efficiency, memorability, and security under the usage scenarios considered in the study.

cs.CR↗

arXiv2026

Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning

Released aligned large language models remain vulnerable to malicious downstream finetuning. Existing defenses are largely designed for the fine-tuning-as-a-service (FTaaS) paradigm or rely on downstream users to follow additional safety procedures, and therefore do not directly address the setting we study: a provider controlled partially protected open-weight (PPOW) release setting in which most weights remain trainable while a small safety-critical component is preserved at release. We propose a Unidirectional Safety Gate (USG), instantiated as a Null Space Cubic Layer together with an Inverse Adapter inserted after the final Transformer layer. During downstream fine-tuning, the cubic layer suppresses or blocks gradients from harmful samples whose hidden states fall in a calibrated protected region, while the Inverse Adapter restores the base model's forward behavior. In practice, we calibrate a threshold using defender-held harmful data, allowing protection to generalize to nearby in-distribution harmful samples. Across six evaluated model-dataset settings, USG keeps post-finetuning attack success rate close to the pre-release level under a fixed release threshold, while maintaining high safe-pass rates on easier settings and exhibiting a clearer safety-utility trade-off on unsafe samples from BeaverTails. These results suggest that release-time representation-space blocking can raise the cost of malicious downstream adaptation without requiring downstream cooperation. The code is available at https://github.com/OpenCausaLab/Gradient-Immunity.

cs.CR↗

arXiv2026

CRAFT: Exploring Wearable Creative AI on Smart Glasses for Fiction Writing in Real-World Contexts

Creative writing increasingly integrates AI assistance, yet current tools miss in-situ moments when writers draw inspiration from real-world experiences. We envision Context-aware Reality-Fiction Transformation (CRAFT), an approach for AI glasses that translates daily experiences into fiction narratives. We explored its desirability, feasibility, and potential viability through three studies. Interviews with nine writers yielded desires and three design goals: 1) augmenting in-situ perception to bridge reality-fiction gaps, 2) promoting authenticity grounded in real-world experiences while maintaining fictionalization, and 3) preserving creative agency, enjoyment, and life-art boundaries. Co-design workshops with 16 writers and researchers operationalized these goals into concrete interaction mechanisms using a technology probe. We then conducted supported field trials with eight writers across 24 sessions using a refined probe, revealing writer-perceived benefits (e.g., enriched fictional ideas from serendipitous encounters), emergent practices (e.g., micro-creation), and design considerations for future sustained use. We contribute design explorations for the CRAFT approach, offering design implications and empirical insights on ubiquitous human-AI creative collaboration in everyday life.

cs.HC↗

arXiv2026

Web2BigTable: A Bi-Level Multi-Agent LLM System for Internet-Scale Information Search and Extraction

Agentic web search increasingly faces two distinct demands: deep reasoning over a single target, and structured aggregation across many entities and heterogeneous sources. Current systems struggle on both fronts. Breadth-oriented tasks demand schema-aligned outputs with wide coverage and cross-entity consistency, while depth-oriented tasks require coherent reasoning over long, branching search trajectories. We introduce \textbf{Web2BigTable}, a multi-agent framework for web-to-table search that supports both regimes. Web2BigTable adopts a bi-level architecture in which an upper-level orchestrator decomposes the task into sub-problems and lower-level worker agents solve them in parallel. Through a closed-loop run--verify--reflect process, the framework jointly improves decomposition and execution over time via persistent, human-readable external memory, with self-evolving updates to each single-agent. During execution, workers coordinate through a shared workspace that makes partial findings visible, allowing them to reduce redundant exploration, reconcile conflicting evidence, and adapt to emerging coverage gaps. Web2BigTable sets a new state of the art on WideSearch, reaching an Avg@4 Success Rate of \textbf{38.50} ($7.5\times$ the second best at 5.10), Row F1 of \textbf{63.53} (+25.03 over the second best), and Item F1 of \textbf{80.12} (+14.42 over the second best). It also generalises to depth-oriented search on XBench-DeepSearch, achieving 73.0 accuracy. Code is available at https://github.com/web2bigtable/web2bigtable.

cs.AI↗

arXiv2026

From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company

Individual agent capabilities have advanced rapidly through modular skills and tool integrations, yet multi-agent systems remain constrained by fixed team structures, tightly coupled coordination logic, and session-bound learning. We argue that this reflects a deeper absence: a principled organisational layer that governs how a workforce of agents is assembled, governed, and improved over time, decoupled from what individual agents know. To fill this gap, we introduce \emph{OneManCompany (OMC)}, a framework that elevates multi-agent systems to the organisational level. OMC encapsulates skills, tools, and runtime configurations into portable agent identities called \emph{Talents}, orchestrated through typed organisational interfaces that abstract over heterogeneous backends. A community-driven \emph{Talent Market} enables on-demand recruitment, allowing the organisation to close capability gaps and reconfigure itself dynamically during execution. Organisational decision-making is operationalised through an \emph{Explore-Execute-Review} ($\text{E}^2$R) tree search, which unifies planning, execution, and evaluation in a single hierarchical loop: tasks are decomposed top-down into accountable units and execution outcomes are aggregated bottom-up to drive systematic review and refinement. This loop provides formal guarantees on termination and deadlock freedom while mirroring the feedback mechanisms of human enterprises. Together, these contributions transform multi-agent systems from static, pre-configured pipelines into self-organising and self-improving AI organisations capable of adapting to open-ended tasks across diverse domains. Empirical evaluation on PRDBench shows that OMC achieves an $84.67\%$ success rate, surpassing the state of the art by $15.48$ percentage points, with cross-domain case studies further demonstrating its generality.

cs.AI↗

arXiv2026

InfoSeeker: A Scalable Hierarchical Parallel Agent Framework for Web Information Seeking

Recent agentic search systems have made substantial progress by emphasising deep, multi-step reasoning. However, this focus often overlooks the challenges of wide-scale information synthesis, where agents must aggregate large volumes of heterogeneous evidence across many sources. As a result, most existing large language model agent systems face severe limitations in data-intensive settings, including context saturation, cascading error propagation, and high end-to-end latency. To address these challenges, we present \framework, a hierarchical framework based on principle of near-decomposability, containing a strategic \textit{Host}, multiple \textit{Managers} and parallel \textit{Workers}. By leveraging aggregation and reflection mechanisms at the Manager layer, our framework enforces strict context isolation to prevent saturation and error propagation. Simultaneously, the parallelism in worker layer accelerates the speed of overall task execution, mitigating the significant latency. Our evaluation on two complementary benchmarks demonstrates both efficiency ($ 3-5 \times$ speed-up) and effectiveness, achieving a $8.4\%$ success rate on WideSearch-en and $52.9\%$ accuracy on BrowseComp-zh. The code is released at https://github.com/agent-on-the-fly/InfoSeeker

cs.AI↗

arXiv2026

Unbounded Systematic Error in Thin Film Conductivity Measurements

Electrical conductivity is the most fundamental charge transport parameter, and measurements of conductivity are a basic part of materials characterization for nearly all conducting materials. In thin films, conductivity is often measured in four bar architectures in which the current source and voltage measurement are spatially separated to eliminate systematic error due to contact resistance. Despite the apparent simplicity of these measurements, we demonstrate here that the four bar architecture is subject to significant systematic error arising from the finite conductivity of the metal electrodes. Remarkably, these systematic errors can in some cases become unbounded, producing arbitrarily high measured conductivity at modest true film conductivities, within the range relevant to emerging thin film thermoelectric materials such as conducting polymers. These unbounded errors, which can occur even in properly conducted four-point measurements of patterned films, likely explain literature reports of extremely high conductivities in conducting polymers, and can lead to anomalous scaling in temperature dependent studies, potentially leading to incorrect interpretation of the relevant charge transport mechanism. We characterize the device geometric factors that control these errors, which stand partially at odds with those required for accurate Seebeck coefficient measurements. Our analyses allow us to identify device architectures that provide small systematic errors for conductivity and Seebeck coefficient while still providing a low measurement resistance, critical to reducing noise in thermal voltage measurements. These findings provide important guidelines for accurate measurements in the growing field of thin-film thermoelectric materials.

cond-mat.mtrl-sci↗

arXiv2026

Secure Text Entry using a Virtual Radial Keyboard with Dynamically Resized Keys and Non-Intrusive Randomization

As virtual reality (VR) becomes more widely adopted, secure and efficient text entry is an increasingly critical need. In this paper, we identify a vulnerability in a state-of-the-art secure VR text entry method and introduce a novel virtual radial keyboard designed to achieve a balance between security with usability. Keys are arranged alphabetically in a circular layout, with each key selected by controller rotation and dynamically expanding to facilitate precise selection. A randomized rotation mechanism shifts the keyboard after each keystroke, preserving relative key positions while disrupting absolute spatial mappings to protect against inference attacks. We conducted a within-subject study (N=30) comparing our method with the prior secure technique and a standard QWERTY keyboard. Results showed that the radial keyboard significantly improves resistance to keystroke prediction attacks while incurring a tradeoff in entry speed and subjective workload due to the unfamiliar non-QWERTY layout. However, both quantitative trends and qualitative feedback indicate strong potential for performance improvements with practice. We also discuss design implications, possible interface refinements, and directions for future work, including layout variations and visual enhancements.

cs.HC↗

arXiv2025

Adapting Like Humans: A Metacognitive Agent with Test-time Reasoning

Recent Vision-Language Models (VLMs) exhibit strong perceptual reasoning abilities, yet they often struggle to adapt efficiently when encountering novel tasks at test time. In contrast, humans leverage the metacognitive model with memory, enabling continuous strategy refinement through metacognitive control when faced with new challenges. To bridge this gap, we propose metacognitive test-time reasoning (MCTR), a framework that equips models with the ability to learn, adapt, and improve during test time through metacognitive self-updating. Inspired by the dual structure of human metacognition, MCTR comprises meta-level and object-level VLM reasoning modules, each equipped with dedicated memory systems for hierarchical adaptive reasoning. Specifically, MCTR consists of (1) a meta-reasoning module which incrementally builds a structured memory by discovering and storing task-relevant rules, environmental patterns, and action-outcome relationships from test-time observations as natural language descriptions; and (2) an action-reasoning module that determines optimal actions through context-aware perception and strategic reasoning by dynamically retrieving and integrating knowledge from memory. The action-reasoning module continuously updates its policy through proposed metacognitive test-time reinforcement learning, adapting as knowledge memory evolves. We evaluate MCTR on 45 Atari games (33 seen, 12 unseen). MCTR demonstrates robust test-time adaptation, achieving 9/12 top-1 results on unseen games compared with baselines. Analyses through ablations, learning dynamics, and case studies reveal the complementary contributions of both components and show meta-reasoning evolving toward human-like adaptation strategies.

cs.AI↗

arXiv2025

CMIS-Net: A Cascaded Multi-Scale Individual Standardization Network for Backchannel Agreement Estimation

Backchannels are subtle listener responses, such as nods, smiles, or short verbal cues like "yes" or "uh-huh," which convey understanding and agreement in conversations. These signals provide feedback to speakers, improve the smoothness of interaction, and play a crucial role in developing human-like, responsive AI systems. However, the expression of backchannel behaviors is often significantly influenced by individual differences, operating across multiple scales: from instant dynamics such as response intensity (frame-level) to temporal patterns such as frequency and rhythm preferences (sequence-level). This presents a complex pattern recognition problem that contemporary emotion recognition methods have yet to fully address. Particularly, existing individualized methods in emotion recognition often operate at a single scale, overlooking the complementary nature of multi-scale behavioral cues. To address these challenges, we propose a novel Cascaded Multi-Scale Individual Standardization Network (CMIS-Net) that extracts individual-normalized backchannel features by removing person-specific neutral baselines from observed expressions. Operating at both frame and sequence levels, this normalization allows model to focus on relative changes from each person's baseline rather than absolute expression values. Furthermore, we introduce an implicit data augmentation module to address the observed training data distributional bias, improving model generalization. Comprehensive experiments and visualizations demonstrate that CMIS-Net effectively handles individual differences and data imbalance, achieving state-of-the-art performance in backchannel agreement detection.

cs.CV↗

arXiv2025

Spiral of Silence in Large Language Model Agents

The Spiral of Silence (SoS) theory holds that individuals with minority views often refrain from speaking out for fear of social isolation, enabling majority positions to dominate public discourse. When the 'agents' are large language models (LLMs), however, the classical psychological explanation is not directly applicable, since SoS was developed for human societies. This raises a central question: can SoS-like dynamics nevertheless emerge from purely statistical language generation in LLM collectives? We propose an evaluation framework for examining SoS in LLM agents. Specifically, we consider four controlled conditions that systematically vary the availability of 'History' and 'Persona' signals. Opinion dynamics are assessed using trend tests such as Mann-Kendall and Spearman's rank, along with concentration measures including kurtosis and interquartile range. Experiments across open-source and closed-source models show that history and persona together produce strong majority dominance and replicate SoS patterns; history signals alone induce strong anchoring; and persona signals alone foster diverse but uncorrelated opinions, indicating that without historical anchoring, SoS dynamics cannot emerge. The work bridges computational sociology and responsible AI design, highlighting the need to monitor and mitigate emergent conformity in LLM-agent systems.

cs.CL↗

arXiv2025

Agentic Web: Weaving the Next Web with AI Agents

The emergence of AI agents powered by large language models (LLMs) marks a pivotal shift toward the Agentic Web, a new phase of the internet defined by autonomous, goal-driven interactions. In this paradigm, agents interact directly with one another to plan, coordinate, and execute complex tasks on behalf of users. This transition from human-driven to machine-to-machine interaction allows intent to be delegated, relieving users from routine digital operations and enabling a more interactive, automated web experience. In this paper, we present a structured framework for understanding and building the Agentic Web. We trace its evolution from the PC and Mobile Web eras and identify the core technological foundations that support this shift. Central to our framework is a conceptual model consisting of three key dimensions: intelligence, interaction, and economics. These dimensions collectively enable the capabilities of AI agents, such as retrieval, recommendation, planning, and collaboration. We analyze the architectural and infrastructural challenges involved in creating scalable agentic systems, including communication protocols, orchestration strategies, and emerging paradigms such as the Agent Attention Economy. We conclude by discussing the potential applications, societal risks, and governance issues posed by agentic systems, and outline research directions for developing open, secure, and intelligent ecosystems shaped by both human intent and autonomous agent behavior. A continuously updated collection of relevant studies for agentic web is available at: https://github.com/SafeRL-Lab/agentic-web.

cs.AI↗

arXiv2025

Spontaneous Spatial Cognition Emerges during Egocentric Video Viewing through Non-invasive BCI

Humans possess a remarkable capacity for spatial cognition, allowing for self-localization even in novel or unfamiliar environments. While hippocampal neurons encoding position and orientation are well documented, the large-scale neural dynamics supporting spatial representation, particularly during naturalistic, passive experience, remain poorly understood. Here, we demonstrate for the first time that non-invasive brain-computer interfaces (BCIs) based on electroencephalography (EEG) can decode spontaneous, fine-grained egocentric 6D pose, comprising three-dimensional position and orientation, during passive viewing of egocentric video. Despite EEG's limited spatial resolution and high signal noise, we find that spatially coherent visual input (i.e., continuous and structured motion) reliably evokes decodable spatial representations, aligning with participants' subjective sense of spatial engagement. Decoding performance further improves when visual input is presented at a frame rate of 100 ms per image, suggesting alignment with intrinsic neural temporal dynamics. Using gradient-based backpropagation through a neural decoding model, we identify distinct EEG channels contributing to position -- and orientation specific -- components, revealing a distributed yet complementary neural encoding scheme. These findings indicate that the brain's spatial systems operate spontaneously and continuously, even under passive conditions, challenging traditional distinctions between active and passive spatial cognition. Our results offer a non-invasive window into the automatic construction of egocentric spatial maps and advance our understanding of how the human mind transforms everyday sensory experience into structured internal representations.

q-bio.NC↗

arXiv2025

Deep Research Agents: A Systematic Examination And Roadmap

The rapid progress of Large Language Models (LLMs) has given rise to a new category of autonomous AI systems, referred to as Deep Research (DR) agents. These agents are designed to tackle complex, multi-turn informational research tasks by leveraging a combination of dynamic reasoning, adaptive long-horizon planning, multi-hop information retrieval, iterative tool use, and the generation of structured analytical reports. In this paper, we conduct a detailed analysis of the foundational technologies and architectural components that constitute Deep Research agents. We begin by reviewing information acquisition strategies, contrasting API-based retrieval methods with browser-based exploration. We then examine modular tool-use frameworks, including code execution, multimodal input processing, and the integration of Model Context Protocols (MCPs) to support extensibility and ecosystem development. To systematize existing approaches, we propose a taxonomy that differentiates between static and dynamic workflows, and we classify agent architectures based on planning strategies and agent composition, including single-agent and multi-agent configurations. We also provide a critical evaluation of current benchmarks, highlighting key limitations such as restricted access to external knowledge, sequential execution inefficiencies, and misalignment between evaluation metrics and the practical objectives of DR agents. Finally, we outline open challenges and promising directions for future research. A curated and continuously updated repository of DR agent research is available at: {https://github.com/ai-agents-2030/awesome-deep-research-agent}.

cs.AI↗

arXiv2025

Synthesis by Design: Controlled Data Generation via Structural Guidance

Mathematical reasoning remains challenging for LLMs due to complex logic and the need for precise computation. Existing methods enhance LLM reasoning by synthesizing datasets through problem rephrasing, but face issues with generation quality and problem complexity. To address this, we propose to extract structural information with generated problem-solving code from mathematical reasoning and guide data generation with structured solutions. Applied to MATH and GSM8K, our approach produces 39K problems with labeled intermediate steps and a 6.1K-problem benchmark of higher difficulty. Results on our benchmark show that model performance declines as reasoning length increases. Additionally, we conducted fine-tuning experiments using the proposed training data on a range of LLMs, and the results validate the effectiveness of our dataset. We hope the proposed method and dataset will contribute to future research in enhancing LLM reasoning capabilities. Our code and data are available at https://github.com/OpenCausaLab/StructuralGeneration.

cs.CL↗

arXiv2025

ATLaS: Agent Tuning via Learning Critical Steps

Large Language Model (LLM) agents have demonstrated remarkable generalization capabilities across multi-domain tasks. Existing agent tuning approaches typically employ supervised finetuning on entire expert trajectories. However, behavior-cloning of full trajectories can introduce expert bias and weaken generalization to states not covered by the expert data. Additionally, critical steps, such as planning, complex reasoning for intermediate subtasks, and strategic decision-making, are essential to success in agent tasks, so learning these steps is the key to improving LLM agents. For more effective and efficient agent tuning, we propose ATLaS that identifies the critical steps in expert trajectories and finetunes LLMs solely on these steps with reduced costs. By steering the training's focus to a few critical steps, our method mitigates the risk of overfitting entire trajectories and promotes generalization across different environments and tasks. In extensive experiments, an LLM finetuned on only 30% critical steps selected by ATLaS outperforms the LLM finetuned on all steps and recent open-source LLM agents. ATLaS maintains and improves base LLM skills as generalist agents interacting with diverse environments.

cs.CL↗

arXiv2024

Domain Structure and Interface Control of Mechanical Stiffness in Sustainable Cellulose Bio-nanocomposites

Renewable and biodegradable plastics derived from soy protein isolate (SPI) offer a promising alternative to conventional petroleum-based plastics, particularly for film-grade bioplastics applications such as plastic bags. However, even with reinforcement from cellulose nanocrystals (CNCs), their mechanical properties including stiffness lag behind those of petroleum-based plastics. To identify pathways for improving CNC-reinforced SPI composites, we studied stiffening mechanisms by interpreting experimental data using homogenization models that accounted for CNC agglomeration and the formation of CNC/SPI interphases. To model effects of surface modification of CNCs with polydopamine (polyDOPA), we incorporated two key mechanisms: enhanced CNC dispersion and modified CNC-SPI interfacial interactions. Models accounted for interphases surrounding CNCs, arising from physicochemical interactions with the polyDOPA-modified CNC surfaces. Consistent wih experimental observations of polyDOPA modification enhancing mechanical properties through both increased spatial distribution of CNCs and matrix-filler interactions, results demonstrated that improved dispersion and interfacial bonding contribute to increased composite stiffness. Results highlight the potential of biodegradable CNC/SPI bio-nanocomposites as sustainable plastic alternatives, and suggest pathways for further enhancing their mechanical properties.

physics.bio-ph↗