Recent research shows that LLM Agents can generate ``believable'' human behaviors via prompt-only methods, and such agents have been increasingly adopted in downstream applications. However, existing evaluation of these agents only focuses on qualitative believability (whether human raters think they are accurate), leaving open questions of whether LLM agents can accurately generate step-by-step actions mimicking a particular human's behavior in a multi-turn interaction task. In this work, we take shopping as a case study and present the first large-scale quantitative evaluation of state-of-the-art LLMs' ability to accurately simulate human behavior. Using real-world data from 31,865 online shopping sessions containing 230,965 user actions, our evaluation reveals that prompt-based LLMs (DeepSeek-R1, Llama, Claude) achieve only 11.86% accuracy in generating human actions, highlighting a substantial gap in actual behavioral accuracy. Through experiments, we also showcase that strategies as simple as fine-tuning LLMs on real human click-through data augmented with synthesized reasoning traces can greatly enhance models' performance. The fine-tuned Qwen2.5-7B achieves 17.26% action generation accuracy and 33.86% F1 score on final purchase prediction, representing substantial improvements of 5.4% and 13.85% over prompt-only baselines. This work establishes the first rigorous benchmark for human behavior simulation and provides actionable insights for developing more accurate LLM agents for future downstream applications.

Extracting medical history entities (MHEs) related to a patient's chief complaint (CC), history of present illness (HPI), and past, family, and social history (PFSH) helps structure free-text clinical notes into standardized EHRs, streamlining downstream tasks like continuity of care, medical coding, and quality metrics. Fine-tuned clinical large language models (cLLMs) can assist in this process while ensuring the protection of sensitive data via on-premises deployment. This study evaluates the performance of cLLMs in recognizing CC/HPI/PFSH-related MHEs and examines how note characteristics impact model accuracy. We annotated 1,449 MHEs across 61 outpatient-related clinical notes from the MTSamples repository. To recognize these entities, we fine-tuned seven state-of-the-art cLLMs. Additionally, we assessed the models' performance when enhanced by integrating, problems, tests, treatments, and other basic medical entities (BMEs). We compared the performance of these models against GPT-4o in a zero-shot setting. To further understand the textual characteristics affecting model accuracy, we conducted an error analysis focused on note length, entity length, and segmentation. The cLLMs showed potential in reducing the time required for extracting MHEs by over 20%. However, detecting many types of MHEs remained challenging due to their polysemous nature and the frequent involvement of non-medical vocabulary. Fine-tuned GatorTron and GatorTronS, two of the most extensively trained cLLMs, demonstrated the highest performance. Integrating pre-identified BME information improved model performance for certain entities. Regarding the impact of textual characteristics on model performance, we found that longer entities were harder to identify, note length did not correlate with a higher error rate, and well-organized segments with headings are beneficial for the extraction.

Backgrounds: Information extraction (IE) is critical in clinical natural language processing (NLP). While large language models (LLMs) excel on generative tasks, their performance on extractive tasks remains debated. Methods: We investigated Named Entity Recognition (NER) and Relation Extraction (RE) using 1,588 clinical notes from four sources (UT Physicians, MTSamples, MIMIC-III, and i2b2). We developed an annotated corpus covering 4 clinical entities and 16 modifiers, and compared instruction-tuned LLaMA-2 and LLaMA-3 against BERT in terms of performance, generalizability, computational resources, and throughput to BERT. Results: LLaMA models outperformed BERT across datasets. With sufficient training data, LLaMA showed modest improvements (1% on NER, 1.5-3.7% on RE); improvements were larger with limited training data. On unseen i2b2 data, LLaMA-3-70B outperformed BERT by 7% (F1) on NER and 4% on RE. However, LLaMA models required more computing resources and ran up to 28 times slower. We implemented "Kiwi," a clinical IE package featuring both models, available at https://kiwi.clinicalnlp.org/. Conclusion: This study is among the first to develop and evaluate a comprehensive clinical IE system using open-source LLMs. Results indicate that LLaMA models outperform BERT for clinical NER and RE but with higher computational costs and lower throughputs. These findings highlight that choosing between LLMs and traditional deep learning methods for clinical IE applications should remain task-specific, taking into account both performance metrics and practical considerations such as available computing resources and the intended use case scenarios.

Building agents with large language models (LLMs) for computer control is a burgeoning research area, where the agent receives computer states and performs actions to complete complex tasks. Previous computer agents have demonstrated the benefits of in-context learning (ICL); however, their performance is hindered by several issues. First, the limited context length of LLMs and complex computer states restrict the number of exemplars, as a single webpage can consume the entire context. Second, the exemplars in current methods, such as high-level plans and multi-choice questions, cannot represent complete trajectories, leading to suboptimal performance in long-horizon tasks. Third, existing computer agents rely on task-specific exemplars and overlook the similarity among tasks, resulting in poor generalization to novel tasks. To address these challenges, we introduce Synapse, a computer agent featuring three key components: i) state abstraction, which filters out task-irrelevant information from raw states, allowing more exemplars within the limited context, ii) trajectory-as-exemplar prompting, which prompts the LLM with complete trajectories of the abstracted states and actions to improve multi-step decision-making, and iii) exemplar memory, which stores the embeddings of exemplars and retrieves them via similarity search for generalization to novel tasks. We evaluate Synapse on MiniWoB++, a standard task suite, and Mind2Web, a real-world website benchmark. In MiniWoB++, Synapse achieves a 99.2% average success rate (a 10% relative improvement) across 64 tasks using demonstrations from only 48 tasks. Notably, Synapse is the first ICL method to solve the book-flight task in MiniWoB++. Synapse also exhibits a 56% relative improvement in average step success rate over the previous state-of-the-art prompting scheme in Mind2Web.

Technological progress benefits people across society, but it can play a special role in supporting people with disabilities. At the intersection between artificial intelligence (AI) and inclusive design is a sweet spot where intelligent machines can enable more people to live independent lives. This sweet spot is what Saqib Shaikh, a Microsoft software engineer who also happens to be blind, is focused on. In 2014, Saqib participated in Microsoft's first company-wide hackathon, developing an idea for using AI to empower individuals with visual impairments. This eventually evolved into Seeing AI.

ML.NET is an open-source and cross-platform machine learning framework (Windows, Linux, macOS) for .NET developers. Using ML.NET, developers can leverage their existing tools and skillsets to develop and infuse custom AI into their applications by creating custom machine learning models for common scenarios like Sentiment Analysis, Recommendation, Image Classification and more!. This release, and all other remaining releases before the v1.0 release, will focus on the overall stability of the framework, continuing to refine the API, fix bugs, reduce the public API surface, and improve documentation and samples. Updates in v0.11 timeframe Added additional ML components to the MLContext catalog, so it--s easier to find the classes and operations to use. Below you can see the experience based on IntelliSense.

Like the Tin Man in The Wizard Of Oz, the robot community has finally found its heart. This time around it's not made of sawdust-stuffed silk. Better -- sensors, cameras, microphones and proprietary algorithms that calculate human emotion according to vocal intonation and facial expressions. And soon it could be ambling around your home, asking if you feel alright, after it goes on sale in Japan from F span class "s1" ebruary 2015 for 198,000 yen ( 1,151.99). Pepper is a Wi-Fi enabled humanoid robot that weighs 28kg, features a 10.1-inch touchscreen and can move at speeds of up to 3km/h.

Any price and availability information displayed on [relevant Amazon Site(s), as applicable] at the time of purchase will apply to the purchase of this product.