LLMs and AI Agents | Dakuo Wanghttps://www.dakuowang.com/tag/llms-and-ai-agents/LLMs and AI AgentsWowchemy (https://wowchemy.com)en-us© 2026 Dakuo WangSun, 08 Nov 2026 00:00:00 +0000https://www.dakuowang.com/media/icon_hu890b44d8e5909e748985cc4bbe27f70d_189660_512x512_fill_lanczos_center_2.pngLLMs and AI Agentshttps://www.dakuowang.com/tag/llms-and-ai-agents/Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIshttps://www.dakuowang.com/publication/lu-2026-firefly/Sun, 08 Nov 2026 00:00:00 +0000https://www.dakuowang.com/publication/lu-2026-firefly/SpanUQ: Span-Level Uncertainty Quantification for Large Language Model Generationhttps://www.dakuowang.com/publication/zhang-2026-spanuq/Sat, 07 Nov 2026 00:00:00 +0000https://www.dakuowang.com/publication/zhang-2026-spanuq/StaRPO: Stability-Augmented Reinforcement Policy Optimizationhttps://www.dakuowang.com/publication/zhang-2026-starpo/Fri, 06 Nov 2026 00:00:00 +0000https://www.dakuowang.com/publication/zhang-2026-starpo/PADFormer: Pose-Agnostic Anomaly Detection from Sparse View Imageshttps://www.dakuowang.com/publication/wang-2026-padformer/Thu, 05 Nov 2026 00:00:00 +0000https://www.dakuowang.com/publication/wang-2026-padformer/Multi-agent-as-judge: Aligning LLM-agent-based automated evaluation with multi-dimensional human evaluationhttps://www.dakuowang.com/publication/chen-2026-multi/Wed, 04 Nov 2026 00:00:00 +0000https://www.dakuowang.com/publication/chen-2026-multi/Can LLM Agents Simulate Multi-Turn Human Behavior? Evidence from Real Online Customer Behavior Datahttps://www.dakuowang.com/publication/lu-2026-can/Tue, 03 Nov 2026 00:00:00 +0000https://www.dakuowang.com/publication/lu-2026-can/LLMs for Now, Fine-Tuning for Later: An Ensemble Approach to Data Drift in Domain-Specific Taskshttps://www.dakuowang.com/publication/lu-2026-llms/Mon, 02 Nov 2026 00:00:00 +0000https://www.dakuowang.com/publication/lu-2026-llms/Agentic Conversational Search with Contextualized Reasoning via Reinforcement Learninghttps://www.dakuowang.com/publication/mo-2026-agentic/Sun, 01 Nov 2026 00:00:00 +0000https://www.dakuowang.com/publication/mo-2026-agentic/On-Policy Self-Distillation for Efficient Diffusion Language Models with Early-Stage Calibrationhttps://www.dakuowang.com/publication/zhu-2026-policy/Sat, 31 Oct 2026 00:00:00 +0000https://www.dakuowang.com/publication/zhu-2026-policy/OPeRA: A Dataset of Observation, Persona, Rationale, and Action for Evaluating LLMs on Human Online Shopping Behavior Simulationhttps://www.dakuowang.com/publication/wang-2026-opera/Sun, 25 Oct 2026 00:00:00 +0000https://www.dakuowang.com/publication/wang-2026-opera/Customer-R1: Personalized Simulation of Human Behaviors via RL-based LLM Agent in Online Shoppinghttps://www.dakuowang.com/publication/wang-2026-customer/Sat, 24 Oct 2026 00:00:00 +0000https://www.dakuowang.com/publication/wang-2026-customer/Trajectory2Task: Training Robust Tool-Calling Agents with Synthesized Yet Verifiable Data for Complex User Intentshttps://www.dakuowang.com/publication/wang-2026-trajectory2task/Fri, 23 Oct 2026 00:00:00 +0000https://www.dakuowang.com/publication/wang-2026-trajectory2task/Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learninghttps://www.dakuowang.com/publication/zhang-2026-shop/Thu, 22 Oct 2026 00:00:00 +0000https://www.dakuowang.com/publication/zhang-2026-shop/SFT Doesn’t Always Hurt General Capabilities: Revisiting Domain-Specific Fine-Tuning in LLMshttps://www.dakuowang.com/publication/lin-2026-sft/Wed, 21 Oct 2026 00:00:00 +0000https://www.dakuowang.com/publication/lin-2026-sft/Agent A/B: Automated and Scalable A/B Testing on Live Websites with Interactive LLM Agentshttps://www.dakuowang.com/publication/lu-2026-agent/Thu, 15 Oct 2026 00:00:00 +0000https://www.dakuowang.com/publication/lu-2026-agent/SurgWound-Bench: A Benchmark for Surgical Wound Diagnosishttps://www.dakuowang.com/publication/xu-2026-surgwound/Tue, 13 Oct 2026 00:00:00 +0000https://www.dakuowang.com/publication/xu-2026-surgwound/Harness updating is not harness benefit: Disentangling evolution capabilities in self-evolving llm agentshttps://www.dakuowang.com/publication/lin-2026-harness/Mon, 12 Oct 2026 00:00:00 +0000https://www.dakuowang.com/publication/lin-2026-harness/“Should I Give Up Now?” Investigating LLM Pitfalls in Software Engineeringhttps://www.dakuowang.com/publication/tie-2026-should/Sun, 11 Oct 2026 00:00:00 +0000https://www.dakuowang.com/publication/tie-2026-should/Evo-harness: Context-to-harness skill compilation for self-evolving agentshttps://www.dakuowang.com/publication/wei-2026-evo/Fri, 09 Oct 2026 00:00:00 +0000https://www.dakuowang.com/publication/wei-2026-evo/The Obvious Invisible Threat: Vulnerabilities of LLM-Powered GUI Agents to Adversarial UI Manipulations in Web Interaction Taskshttps://www.dakuowang.com/publication/chen-2026-obvious/Wed, 07 Oct 2026 00:00:00 +0000https://www.dakuowang.com/publication/chen-2026-obvious/Large Language Models with Temporal Reasoning for Longitudinal Clinical Summarization and Predictionhttps://www.dakuowang.com/publication/kruse-2025-large/Tue, 30 Dec 2025 00:00:00 +0000https://www.dakuowang.com/publication/kruse-2025-large/Towards a Design Guideline for RPA Evaluation: A Survey of Large Language Model-Based Role-Playing Agentshttps://www.dakuowang.com/publication/chen-2025-towards/Mon, 29 Dec 2025 00:00:00 +0000https://www.dakuowang.com/publication/chen-2025-towards/SepsisCalc: Integrating Clinical Calculators into Early Sepsis Prediction via Dynamic Temporal Graph Constructionhttps://www.dakuowang.com/publication/yin-2025-sepsiscalc/Mon, 22 Dec 2025 00:00:00 +0000https://www.dakuowang.com/publication/yin-2025-sepsiscalc/UXAgent: An LLM Agent-Based Usability Testing Framework for Web Designhttps://www.dakuowang.com/publication/lu-2025-uxagent/Fri, 19 Dec 2025 00:00:00 +0000https://www.dakuowang.com/publication/lu-2025-uxagent/Will the Prince Get True Love’s Kiss? On the Model Sensitivity to Gender Perturbation over Fairytale Textshttps://www.dakuowang.com/publication/chance-2025-will/Wed, 17 Dec 2025 00:00:00 +0000https://www.dakuowang.com/publication/chance-2025-will/WEBSERV: A Browser-Server Environment for Efficient Training of Reinforcement Learning-based Web Agents at Scalehttps://www.dakuowang.com/publication/lu-2025-webserv/Sun, 14 Dec 2025 00:00:00 +0000https://www.dakuowang.com/publication/lu-2025-webserv/StorySpark: Expert-Annotated QA Pairs with Real-World Knowledge for Children Storytellinghttps://www.dakuowang.com/publication/chen-2024-storyspark/Tue, 31 Dec 2024 00:00:00 +0000https://www.dakuowang.com/publication/chen-2024-storyspark/More Samples or More Prompts? Exploring Effective Few-Shot In-Context Learning for LLMs with In-Context Samplinghttps://www.dakuowang.com/publication/yao-2024-more/Thu, 26 Dec 2024 00:00:00 +0000https://www.dakuowang.com/publication/yao-2024-more/SepsisLab: Early Sepsis Prediction with Uncertainty Quantification and Active Sensinghttps://www.dakuowang.com/publication/yin-2024-sepsislab/Sat, 21 Dec 2024 00:00:00 +0000https://www.dakuowang.com/publication/yin-2024-sepsislab/More Samples or More Prompt Inputs? Exploring Effective In-Context Sampling for LLM Few-Shot Prompt Engineeringhttps://www.dakuowang.com/publication/yao-2024-more-2/Wed, 18 Dec 2024 00:00:00 +0000https://www.dakuowang.com/publication/yao-2024-more-2/Evaluating the LLM Agents for Simulating Humanoid Behaviorhttps://www.dakuowang.com/publication/chen-2024-evaluating/Sun, 15 Dec 2024 00:00:00 +0000https://www.dakuowang.com/publication/chen-2024-evaluating/Understanding the Daily Lives of Older Adults: Integrating Multi-modal Personal Health Tracking Data through Visualization and Large Language Modelshttps://www.dakuowang.com/publication/li-2024-understanding/Sat, 14 Dec 2024 00:00:00 +0000https://www.dakuowang.com/publication/li-2024-understanding/Challenges and Opportunities of LLM-Based Synthetic Personae and Data in HCIhttps://www.dakuowang.com/publication/prpa-2024-challenges/Thu, 12 Dec 2024 00:00:00 +0000https://www.dakuowang.com/publication/prpa-2024-challenges/‘Don’t Get Too Technical with Me’: A Discourse Structure-Based Framework for Automatic Science Journalismhttps://www.dakuowang.com/publication/cardenas-2023-don/Sun, 31 Dec 2023 00:00:00 +0000https://www.dakuowang.com/publication/cardenas-2023-don/Beyond Labels: Empowering Human with Natural Language Explanations through a Novel Active-Learning Architecturehttps://www.dakuowang.com/publication/yao-2023-beyond/Sat, 30 Dec 2023 00:00:00 +0000https://www.dakuowang.com/publication/yao-2023-beyond/Are human explanations always helpful? towards objective evaluation of human natural language explanationshttps://www.dakuowang.com/publication/yao-2023-are/Thu, 28 Dec 2023 00:00:00 +0000https://www.dakuowang.com/publication/yao-2023-are/MBTI Personality Prediction for Fictional Characters Using Movie Scriptshttps://www.dakuowang.com/publication/sang-2022-mbti/Sat, 31 Dec 2022 00:00:00 +0000https://www.dakuowang.com/publication/sang-2022-mbti/Towards a Progression-Aware Autonomous Dialogue Agenthttps://www.dakuowang.com/publication/sanders-2022-towards/Fri, 30 Dec 2022 00:00:00 +0000https://www.dakuowang.com/publication/sanders-2022-towards/A Word is Worth A Thousand Dollars: Adversarial Attack on Tweets Fools Stock Predictionhttps://www.dakuowang.com/publication/xie-2022-word/Thu, 29 Dec 2022 00:00:00 +0000https://www.dakuowang.com/publication/xie-2022-word/Educational Question Generation of Children Storybooks via Question Type Distribution Learning and Event-Centric Summarizationhttps://www.dakuowang.com/publication/zhao-2022-educational/Mon, 26 Dec 2022 00:00:00 +0000https://www.dakuowang.com/publication/zhao-2022-educational/It is AI’s Turn to Ask Humans a Question: Question-Answer Pair Generation for Children’s Story Bookshttps://www.dakuowang.com/publication/yao-2022-it/Sun, 25 Dec 2022 00:00:00 +0000https://www.dakuowang.com/publication/yao-2022-it/Fantastic Questions and Where to Find Them: FairytaleQA–An Authentic Dataset for Narrative Comprehensionhttps://www.dakuowang.com/publication/xu-2022-fantastic/Sat, 24 Dec 2022 00:00:00 +0000https://www.dakuowang.com/publication/xu-2022-fantastic/Semantic Feature Discovery with Code Mining and Semantic Type Detectionhttps://www.dakuowang.com/publication/srinivas-2022-semantic/Sun, 18 Dec 2022 00:00:00 +0000https://www.dakuowang.com/publication/srinivas-2022-semantic/Gemv2: Multilingual nlg benchmarking in a single line of codehttps://www.dakuowang.com/publication/gehrmann-2022-gemv2/Thu, 15 Dec 2022 00:00:00 +0000https://www.dakuowang.com/publication/gehrmann-2022-gemv2/Label Sleuth: From unlabeled text to a classifier in a few hourshttps://www.dakuowang.com/publication/shnarch-2022-label/Mon, 12 Dec 2022 00:00:00 +0000https://www.dakuowang.com/publication/shnarch-2022-label/DeepBrain: Enabling Fine-Grained Brain-Robot Interaction through Human-Centered Learning of Coarse EEG Signals from Low-Cost Deviceshttps://www.dakuowang.com/publication/wu-2022-deepbrain/Sat, 10 Dec 2022 00:00:00 +0000https://www.dakuowang.com/publication/wu-2022-deepbrain/HAConvGNN: Hierarchical Attention Based Convolutional Graph Neural Network for Code Documentation Generation in Jupyter Notebookshttps://www.dakuowang.com/publication/liu-2021-haconvgnn/Fri, 31 Dec 2021 00:00:00 +0000https://www.dakuowang.com/publication/liu-2021-haconvgnn/D2S: Document-to-Slide Generation Via Query-Based Text Summarizationhttps://www.dakuowang.com/publication/sun-2021-d2s/Thu, 30 Dec 2021 00:00:00 +0000https://www.dakuowang.com/publication/sun-2021-d2s/Graph-Augmented Code Summarization in Computational Notebookshttps://www.dakuowang.com/publication/wang-2021-graph/Fri, 24 Dec 2021 00:00:00 +0000https://www.dakuowang.com/publication/wang-2021-graph/Automated data science for relational datahttps://www.dakuowang.com/publication/lam-2021-automated/Thu, 23 Dec 2021 00:00:00 +0000https://www.dakuowang.com/publication/lam-2021-automated/Data-debugging through interactive visual explanationshttps://www.dakuowang.com/publication/afzal-2021-data/Wed, 22 Dec 2021 00:00:00 +0000https://www.dakuowang.com/publication/afzal-2021-data/Autotext: An end-to-end autoai framework for texthttps://www.dakuowang.com/publication/chaudhary-2021-autotext/Sun, 19 Dec 2021 00:00:00 +0000https://www.dakuowang.com/publication/chaudhary-2021-autotext/An ADMM based framework for automl pipeline configurationhttps://www.dakuowang.com/publication/liu-2020-admm/Sun, 27 Dec 2020 00:00:00 +0000https://www.dakuowang.com/publication/liu-2020-admm/IBM AutoAI: Human-in-the-Loop Automated Machine Learning Supports Data Scientists to Build Better Models.https://www.dakuowang.com/publication/wang-2020-ibm/Sun, 20 Dec 2020 00:00:00 +0000https://www.dakuowang.com/publication/wang-2020-ibm/Context-aware conversation thread detection in multi-party chathttps://www.dakuowang.com/publication/tan-2019-context/Mon, 30 Dec 2019 00:00:00 +0000https://www.dakuowang.com/publication/tan-2019-context/Out-of-domain detection for low-resource text classification taskshttps://www.dakuowang.com/publication/tan-2019-out/Sun, 29 Dec 2019 00:00:00 +0000https://www.dakuowang.com/publication/tan-2019-out/Extracting multiple-relations in one-pass with pre-trained transformershttps://www.dakuowang.com/publication/wang-2019-extracting/Fri, 27 Dec 2019 00:00:00 +0000https://www.dakuowang.com/publication/wang-2019-extracting/