arXiv subjects

Haolun Wu

Publications and source records attributed to Haolun Wu.

At least 37 records · Page 2Linked to original sources

arXiv2026

Beyond Message Passing: A Semantic View of Agent Communication Protocols

Agent communication protocols are becoming critical infrastructure for large language model (LLM) systems that must use tools, coordinate with other agents, and operate across heterogeneous environments. This work presents a human-inspired perspective on this emerging landscape by organizing agent communication into three layers: communication, syntactic, and semantic. Under this framework, we systematically analyze 18 representative protocols and compare how they support reliable transport, structured interaction, and meaning-level coordination. Our analysis shows a clear imbalance in current protocol design. Most protocols provide increasingly mature support for transport, streaming, schema definition, and lifecycle management, but offer limited protocol-level mechanisms for clarification, context alignment, and verification. As a result, semantic responsibilities are often pushed into prompts, wrappers, or application-specific orchestration logic, creating hidden interoperability and maintenance costs. To make this gap actionable, we further identify major forms of technical debt in today's protocol ecosystem and distill practical guidance for selecting protocols under different deployment settings. We conclude by outlining a research agenda for interoperable, secure, and semantically robust agent ecosystems that move beyond message passing toward shared understanding.

cs.NI↗

arXiv2026

"I Use ChatGPT to Humanize My Words": Affordances and Risks of ChatGPT to Autistic Users

Large Language Model (LLM) chatbots like ChatGPT have emerged as cognitive scaffolding for autistic users, yet the tension between their utility and risk remains under-articulated. Through an inductive thematic analysis of 3,984 social media posts by self-identified autistic users, we apply a technology affordance lens to examine this duality. We found that while users leveraged ChatGPT to offload executive dysfunction, regulate emotions, translate neurotypical communication, and validate their autistic identity, these affordances coexist with risks to their well-being: reinforcing delusional thinking, erasing authentic identity through automated masking, and triggering conflicts with the autistic sense of justice. As part of our preliminary work, this poster identifies trade-offs in autistic users' interactions with ChatGPT and concludes by outlining our future work on developing neuro-inclusive technologies that address these tensions through beneficial friction, bidirectional translation, and the delineation of emotional validation from reality.

cs.HC↗

arXiv2026

Aligning Compound AI Systems via System-level DPO

Compound AI systems, comprising multiple interacting components such as LLMs, foundation models, and external tools, have demonstrated remarkable improvements compared to single models in various tasks. To ensure their effective deployment in real-world applications, aligning these systems with human preferences is crucial. However, aligning the compound system via policy optimization, unlike the alignment of a single model, is challenging for two main reasons: (i) non-differentiable interactions between components make end-to-end gradient-based optimization method inapplicable, and (ii) system-level preferences cannot be directly transformed into component-level preferences. To address these challenges, we first formulate compound AI systems as Directed Acyclic Graphs (DAGs), explicitly modeling both component interactions and the associated data flows. Building on this formulation, we introduce $\textbf{SysDPO}$, a framework that extends Direct Preference Optimization (DPO) to enable joint system-level alignment. We propose two variants, SysDPO-Direct and SysDPO-Sampling, tailored for scenarios depending on whether we construct a system-specific preference dataset. We empirically demonstrate the effectiveness of our approach across two applications: the joint alignment of a language model and a diffusion model, and the joint alignment of an LLM collaboration system.

cs.LG↗

arXiv2026

Give Users the Wheel: Towards Promptable Recommendation Paradigm

Conventional sequential recommendation models have achieved remarkable success in mining implicit behavioral patterns. However, these architectures remain structurally blind to explicit user intent: they struggle to adapt when a user's immediate goal (e.g., expressed via a natural language prompt) deviates from their historical habits. While Large Language Models (LLMs) offer the semantic reasoning to interpret such intent, existing integration paradigms force a dilemma: LLM-as-a-recommender paradigm sacrifices the efficiency and collaborative precision of ID-based retrieval, while Reranking methods are inherently bottlenecked by the recall capabilities of the underlying model. In this paper, we propose Decoupled Promptable Sequential Recommendation (DPR), a model-agnostic framework that empowers conventional sequential backbones to natively support Promptable Recommendation, the ability to dynamically steer the retrieval process using natural language without abandoning collaborative signals. DPR modulates the latent user representation directly within the retrieval space. To achieve this, we introduce a Fusion module to align the collaborative and semantic signals, a Mixture-of-Experts (MoE) architecture that disentangles the conflicting gradients from positive and negative steering, and a three-stage training strategy that progressively aligns the semantic space of prompts with the collaborative space. Extensive experiments on real-world datasets demonstrate that DPR significantly outperforms state-of-the-art baselines in prompt-guided tasks while maintaining competitive performance in standard sequential recommendation scenarios.

cs.IR↗

arXiv2025

LLM Use for Mental Health: Crowdsourcing Users' Sentiment-based Perspectives and Values from Social Discussions

Large language models (LLMs) chatbots like ChatGPT are increasingly used for mental health support. They offer accessible, therapeutic support but also raise concerns about misinformation, over-reliance, and risks in high-stakes contexts of mental health. We crowdsource large-scale users' posts from six major social media platforms to examine how people discuss their interactions with LLM chatbots across different mental health conditions. Through an LLM-assisted pipeline grounded in Value-Sensitive Design (VSD), we mapped the relationships across user-reported sentiments, mental health conditions, perspectives, and values. Our results reveal that the use of LLM chatbots is condition-specific. Users with neurodivergent conditions (e.g., ADHD, ASD) report strong positive sentiments and instrumental or appraisal support, whereas higher-risk disorders (e.g., schizophrenia, bipolar disorder) show more negative sentiments. We further uncover how user perspectives co-occur with underlying values, such as identity, autonomy, and privacy. Finally, we discuss shifting from "one-size-fits-all" chatbot design toward condition-specific, value-sensitive LLM design.

cs.CY↗

arXiv2025

Privis: Towards Content-Aware Secure Volumetric Video Delivery

Volumetric video has emerged as a key paradigm in eXtended Reality (XR) and immersive multimedia because it enables highly interactive, spatially consistent 3D experiences. However, the transport-layer security for such 3D content remains largely unaddressed. Existing volumetric streaming pipelines inherit uniform encryption schemes from 2D video, overlooking the heterogeneous privacy sensitivity of different geometry and the strict motion-to-photon latency constraints of real-time XR. We take an initial step toward content-aware secure volumetric video delivery by introducing Privis, a saliency-guided transport framework that (i) partitions volumetric assets into independent units, (ii) applies lightweight authenticated encryption with adaptive key rotation, and (iii) employs selective traffic shaping to balance confidentiality and low latency. Privis specifies a generalized transport-layer security architecture for volumetric media, defining core abstractions and adaptive protection mechanisms. We further explore a prototype implementation and present initial latency measurements to illustrate feasibility and design tradeoffs, providing early empirical guidance toward future work on real-time, saliency-conditioned secure delivery.

cs.CR↗

arXiv2025

Can LLM Agents Really Debate? A Controlled Study of Multi-Agent Debate in Logical Reasoning

Multi-agent debate (MAD) has recently emerged as a promising framework for improving the reasoning performance of large language models (LLMs). Yet, whether LLM agents can genuinely engage in deliberative reasoning, beyond simple ensembling or majority voting, remains unclear. We address this question through a controlled study using the Knight--Knave--Spy logic puzzle, which enables precise, step-wise evaluation of debate outcomes and processes under verifiable ground truth. We systematically set up six structural and cognitive factors, including agent team size, composition, confidence visibility, debate order, debate depth, and task difficulty, to disentangle their respective effects on collective reasoning. Our results show that intrinsic reasoning strength and group diversity are the dominant drivers of debate success, while structural parameters such as order or confidence visibility offer limited gains. Beyond outcomes, process-level analyses identify key behavioral patterns: majority pressure suppresses independent correction, effective teams overturn incorrect consensus, and rational, validity-aligned reasoning most strongly predicts improvement. These findings provide valuable insights into how and why LLM debates succeed or fail, offering guidance for designing interpretable and truth-seeking multi-agent reasoning systems.

cs.MA↗

arXiv2025

PartnerMAS: An LLM Hierarchical Multi-Agent Framework for Business Partner Selection on High-Dimensional Features

High-dimensional decision-making tasks, such as business partner selection, involve evaluating large candidate pools with heterogeneous numerical, categorical, and textual features. While large language models (LLMs) offer strong in-context reasoning capabilities, single-agent or debate-style systems often struggle with scalability and consistency in such settings. We propose PartnerMAS, a hierarchical multi-agent framework that decomposes evaluation into three layers: a Planner Agent that designs strategies, Specialized Agents that perform role-specific assessments, and a Supervisor Agent that integrates their outputs. To support systematic evaluation, we also introduce a curated benchmark dataset of venture capital co-investments, featuring diverse firm attributes and ground-truth syndicates. Across 140 cases, PartnerMAS consistently outperforms single-agent and debate-based multi-agent baselines, achieving up to 10--15\% higher match rates. Analysis of agent reasoning shows that planners are most responsive to domain-informed prompts, specialists produce complementary feature coverage, and supervisors play an important role in aggregation. Our findings demonstrate that structured collaboration among LLM agents can generate more robust outcomes than scaling individual models, highlighting PartnerMAS as a promising framework for high-dimensional decision-making in data-rich domains.

cs.MA↗

arXiv2025

Linking Facial Recognition of Emotions and Socially Shared Regulation in Medical Simulation

Computer-supported simulation enables a practical alternative for medical training purposes. This study investigates the co-occurrence of facial-recognition-derived emotions and socially shared regulation of learning (SSRL) interactions in a medical simulation training context. Using transmodal analysis (TMA), we compare novice and expert learners' affective and cognitive engagement patterns during collaborative virtual diagnosis tasks. Results reveal that expert learners exhibit strong associations between socio-cognitive interactions and high-arousal emotions (surprise, anger), suggesting focused, effortful engagement. In contrast, novice learners demonstrate stronger links between socio-cognitive processes and happiness or sadness, with less coherent SSRL patterns, potentially indicating distraction or cognitive overload. Transmodal analysis of multimodal data (facial expressions and discourse) highlights distinct regulatory strategies between groups, offering methodological and practical insights for computer-supported cooperative work (CSCW) in medical education. Our findings underscore the role of emotion-regulation dynamics in collaborative expertise development and suggest the need for tailored scaffolding to support novice learners' socio-cognitive and affective engagement.

cs.HC↗

arXiv2025

Audio Prototypical Network For Controllable Music Recommendation

Traditional recommendation systems represent user preferences in dense representations obtained through black-box encoder models. While these models often provide strong recommendation performance, they lack interpretability for users, leaving users unable to understand or control the system's modeling of their preferences. This limitation is especially challenging in music recommendation, where user preferences are highly personal and often evolve based on nuanced qualities like mood, genre, tempo, or instrumentation. In this paper, we propose an audio prototypical network for controllable music recommendation. This network expresses user preferences in terms of prototypes representative of semantically meaningful features pertaining to musical qualities. We show that the model obtains competitive recommendation performance compared to popular baseline models while also providing interpretable and controllable user profiles.

cs.IR↗

arXiv2025

Timing is Important: Risk-aware Fund Allocation based on Time-Series Forecasting

Fund allocation has been an increasingly important problem in the financial domain. In reality, we aim to allocate the funds to buy certain assets within a certain future period. Naive solutions such as prediction-only or Predict-then-Optimize approaches suffer from goal mismatch. Additionally, the introduction of the SOTA time series forecasting model inevitably introduces additional uncertainty in the predicted result. To solve both problems mentioned above, we introduce a Risk-aware Time-Series Predict-and-Allocate (RTS-PnO) framework, which holds no prior assumption on the forecasting models. Such a framework contains three features: (i) end-to-end training with objective alignment measurement, (ii) adaptive forecasting uncertainty calibration, and (iii) agnostic towards forecasting models. The evaluation of RTS-PnO is conducted over both online and offline experiments. For offline experiments, eight datasets from three categories of financial applications are used: Currency, Stock, and Cryptos. RTS-PnO consistently outperforms other competitive baselines. The online experiment is conducted on the Cross-Border Payment business at FiT, Tencent, and an 8.4\% decrease in regret is witnessed when compared with the product-line approach. The code for the offline experiment is available at https://github.com/fuyuanlyu/RTS-PnO.

cs.LG↗

arXiv2025

Counterfactual Multi-player Bandits for Explainable Recommendation Diversification

Existing recommender systems tend to prioritize items closely aligned with users' historical interactions, inevitably trapping users in the dilemma of ``filter bubble''. Recent efforts are dedicated to improving the diversity of recommendations. However, they mainly suffer from two major issues: 1) a lack of explainability, making it difficult for the system designers to understand how diverse recommendations are generated, and 2) limitations to specific metrics, with difficulty in enhancing non-differentiable diversity metrics. To this end, we propose a \textbf{C}ounterfactual \textbf{M}ulti-player \textbf{B}andits (CMB) method to deliver explainable recommendation diversification across a wide range of diversity metrics. Leveraging a counterfactual framework, our method identifies the factors influencing diversity outcomes. Meanwhile, we adopt the multi-player bandits to optimize the counterfactual optimization objective, making it adaptable to both differentiable and non-differentiable diversity metrics. Extensive experiments conducted on three real-world datasets demonstrate the applicability, effectiveness, and explainability of the proposed CMB.

cs.IR↗

arXiv2025

Understanding 6G through Language Models: A Case Study on LLM-aided Structured Entity Extraction in Telecom Domain

Knowledge understanding is a foundational part of envisioned 6G networks to advance network intelligence and AI-native network architectures. In this paradigm, information extraction plays a pivotal role in transforming fragmented telecom knowledge into well-structured formats, empowering diverse AI models to better understand network terminologies. This work proposes a novel language model-based information extraction technique, aiming to extract structured entities from the telecom context. The proposed telecom structured entity extraction (TeleSEE) technique applies a token-efficient representation method to predict entity types and attribute keys, aiming to save the number of output tokens and improve prediction accuracy. Meanwhile, TeleSEE involves a hierarchical parallel decoding method, improving the standard encoder-decoder architecture by integrating additional prompting and decoding strategies into entity extraction tasks. In addition, to better evaluate the performance of the proposed technique in the telecom domain, we further designed a dataset named 6GTech, including 2390 sentences and 23747 words from more than 100 6G-related technical publications. Finally, the experiment shows that the proposed TeleSEE method achieves higher accuracy than other baseline techniques, and also presents 5 to 9 times higher sample processing speed.

cs.CL↗

arXiv2025

SSRLBot: Designing and Developing a Large Language Model-based Agent using Socially Shared Regulated Learning

Large language model (LLM)--based agents have emerged as pivotal tools in assisting human experts across various fields by transforming complex tasks into more efficient workflows and providing actionable stakeholder insights. Despite their potential, the application of LLM-based agents for medical education remains underexplored. The study aims to assist in evaluating the students' process and outcomes on medical case diagnosis and discussion while incorporating the theoretical framework of Socially Shared Regulation of Learning (SSRL) to assess student performance. SSRL emphasizes metacognitive, cognitive, motivational, and emotional interactions, highlighting the collaborative management of learning processes to improve decision-making outcomes. Grounded in SSRL theory, this tool paper introduces SSRLBot, an LLM-based agent designed to enable team members to reflect on their diagnostic performance and the key SSRL skills that foster team success. SSRLBot's core functions include summarizing dialogue content, analyzing participants' SSRL skills, and evaluating students' diagnostic results. Meanwhile, we evaluated SSRLBot through diagnostic conversation data collected from six groups (12 participants, 1926 conversational turns). Results showed that SSRLBot can deliver detailed, theory-aligned evaluations, link specific behaviors to SSRL dimensions, and offer actionable recommendations for improving teamwork. The findings address a critical gap in medical education, advancing the application of LLM agents to enhance team-based decision-making and collaboration in high-stakes environments.

cs.HC↗

arXiv2025

A Survey on Test-Time Scaling in Large Language Models: What, How, Where, and How Well?

As enthusiasm for scaling computation (data and parameters) in the pretraining era gradually diminished, test-time scaling (TTS), also referred to as ``test-time computing'' has emerged as a prominent research focus. Recent studies demonstrate that TTS can further elicit the problem-solving capabilities of large language models (LLMs), enabling significant breakthroughs not only in specialized reasoning tasks, such as mathematics and coding, but also in general tasks like open-ended Q&A. However, despite the explosion of recent efforts in this area, there remains an urgent need for a comprehensive survey offering a systemic understanding. To fill this gap, we propose a unified, multidimensional framework structured along four core dimensions of TTS research: what to scale, how to scale, where to scale, and how well to scale. Building upon this taxonomy, we conduct an extensive review of methods, application scenarios, and assessment aspects, and present an organized decomposition that highlights the unique functional roles of individual techniques within the broader TTS landscape. From this analysis, we distill the major developmental trajectories of TTS to date and offer hands-on guidelines for practical deployment. Furthermore, we identify several open challenges and offer insights into promising future directions, including further scaling, clarifying the functional essence of techniques, generalizing to more tasks, and more attributions. Our repository is available on https://github.com/testtimescaling/testtimescaling.github.io/

cs.CL↗

arXiv2025

What Makes Teamwork Work? A Multimodal Case Study on Emotions and Diagnostic Expertise in an Intelligent Tutoring System

Teamwork is pivotal in medical teamwork when professionals with diverse skills and emotional states collaborate to make critical decisions. This case study examines the interplay between emotions and professional skills in group decision-making during collaborative medical diagnosis within an Intelligent Tutoring System (ITS). By comparing verbal and physiological data between high-performing and low-performing teams of medical professionals working on a patient case within the ITS, alongside individuals' retrospective collaboration experiences, we employ multimodal data analysis to identify patterns in team emotional climate and their impact on diagnostic efficiency. Specifically, we investigate how emotion-driven dialogue and professional expertise influence both the information-seeking process and the final diagnostic decisions. Grounded in the socially shared regulation of learning framework and utilizing sentiment analysis, we found that social-motivational interactions are key drivers of a positive team emotional climate. Furthermore, through content analysis of dialogue and physiological signals to pinpoint emotional fluctuations, we identify episodes where knowledge exchange and skill acquisition are most likely to occur. Our findings offer valuable insights into optimizing group collaboration in medical contexts by harmonizing emotional dynamics with adaptive strategies for effective decision-making, ultimately enhancing diagnostic accuracy and teamwork effectiveness.

cs.HC↗

arXiv2025

Design Editing for Offline Model-based Optimization

Offline model-based optimization (MBO) aims to maximize a black-box objective function using only an offline dataset of designs and scores. These tasks span various domains, such as robotics, material design, and protein and molecular engineering. A common approach involves training a surrogate model using existing designs and their corresponding scores, and then generating new designs through gradient-based updates with respect to the surrogate model. This method suffers from the out-of-distribution issue, where the surrogate model may erroneously predict high scores for unseen designs. To address this challenge, we introduce a novel method, Design Editing for Offline Model-based Optimization (DEMO), which leverages a diffusion prior to calibrate overly optimized designs. DEMO first generates pseudo design candidates by performing gradient ascent with respect to a surrogate model. While these pseudo design candidates contain information beyond the offline dataset, they might be invalid or have erroneously high predicted scores. Therefore, to address this challenge while utilizing the information provided by pseudo design candidates, we propose an editing process to refine these pseudo design candidates. We introduce noise to the pseudo design candidates and subsequently denoise them with a diffusion prior trained on the offline dataset, ensuring they align with the distribution of valid designs. Empirical evaluations on seven offline MBO tasks show that, with properly tuned hyperparameters, DEMOs score is competitive with the best previously reported scores in the literature.

cs.LG↗

arXiv2025

TEARS: Textual Representations for Scrutable Recommendations

Traditional recommender systems rely on high-dimensional (latent) embeddings for modeling user-item interactions, often resulting in opaque representations that lack interpretability. Moreover, these systems offer limited control to users over their recommendations. Inspired by recent work, we introduce TExtuAl Representations for Scrutable recommendations (TEARS) to address these challenges. Instead of representing a user's interests through a latent embedding, TEARS encodes them in natural text, providing transparency and allowing users to edit them. To do so, TEARS uses a modern LLM to generate user summaries based on user preferences. We find the summaries capture user preferences uniquely. Using these summaries, we take a hybrid approach where we use an optimal transport procedure to align the summaries' representation with the learned representation of a standard VAE for collaborative filtering. We find this approach can surpass the performance of three popular VAE models while providing user-controllable recommendations. We also analyze the controllability of TEARS through three simulated user tasks to evaluate the effectiveness of a user editing its summary.

cs.IR↗