Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks

Modern AI agents, driven by advances in large foundation models, promise to enhance our productivity and transform our lives by augmenting our knowledge and capabilities. To achieve this vision, AI agents must effectively plan, perform multi-step reasoning and actions, respond to novel observations, and recover from errors, to successfully complete complex tasks across a wide range of scenarios. In this work, we introduce Magentic-One, a high-performing open-source agentic system for solving such tasks. Magentic-One uses a multi-agent architecture where a lead agent, the Orchestrator, plans, tracks progress, and re-plans to recover from errors. Throughout task execution, the Orchestrator directs other specialized agents to perform tasks as needed, such as operating a web browser, navigating local files, or writing and executing Python code. We show that Magentic-One achieves statistically competitive performance to the state-of-the-art on three diverse and challenging agentic benchmarks: GAIA, AssistantBench, and WebArena. Magentic-One achieves these results without modification to core agent capabilities or to how they collaborate, demonstrating progress towards generalist agentic systems. Moreover, Magentic-One's modular design allows agents to be added or removed from the team without additional prompt tuning or training, easing development and making it extensible to future scenarios. We provide an open-source implementation of Magentic-One, and we include AutoGenBench, a standalone tool for agentic evaluation. AutoGenBench provides built-in controls for repetition and isolation to run agentic benchmarks in a rigorous and contained manner -- which is important when agents' actions have side-effects. Magentic-One, AutoGenBench and detailed empirical performance evaluations of Magentic-One, including ablations and error analysis are available at https://aka.ms/magentic-one

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Framework

This technical report presents AutoGen, a new framework that enables development of LLM applications using multiple agents that can converse with each other to solve tasks. AutoGen agents are customizable, conversable, and seamlessly allow human participation. They can operate in various modes that employ combinations of LLMs, human inputs, and tools. AutoGen's design offers multiple advantages: a) it gracefully navigates the strong but imperfect generation and reasoning abilities of these LLMs; b) it leverages human understanding and intelligence, while providing valuable automation through conversations between agents; c) it simplifies and unifies the implementation of complex LLM workflows as automated agent chats. We provide many diverse examples of how developers can easily use AutoGen to effectively solve tasks or build applications, ranging from coding, mathematics, operations research, entertainment, online decision-making, question answering, etc.

When to Show a Suggestion? Integrating Human Feedback in AI-Assisted Programming

AI powered code-recommendation systems, such as Copilot and CodeWhisperer, provide code suggestions inside a programmer's environment (e.g., an IDE) with the aim to improve their productivity. Since, in these scenarios, programmers accept and reject suggestions, ideally, such a system should use this feedback in furtherance of this goal. In this work we leverage prior data of programmers interacting with Copilot to develop interventions that can save programmer time. We propose a utility theory framework, which models this interaction with programmers and decides when and which suggestions to display. Our framework Conditional suggestion Display from Human Feedback (CDHF) is based on predictive models of programmer actions. Using data from 535 programmers we build models that predict the likelihood of suggestion acceptance. In a retrospective evaluation on real-world programming tasks solved with AI-assisted programming, we find that CDHF can achieve favorable tradeoffs. Our findings show the promise of integrating human feedback to improve interaction with large language models in scenarios such as programming and possibly writing tasks.

Generation Probabilities Are Not Enough: Exploring the Effectiveness of Uncertainty Highlighting in AI-Powered Code Completions

Large-scale generative models enabled the development of AI-powered code completion tools to assist programmers in writing code. However, much like other AI-powered tools, AI-powered code completions are not always accurate, potentially introducing bugs or even security vulnerabilities into code if not properly detected and corrected by a human programmer. One technique that has been proposed and implemented to help programmers identify potential errors is to highlight uncertain tokens. However, there have been no empirical studies exploring the effectiveness of this technique-- nor investigating the different and not-yet-agreed-upon notions of uncertainty in the context of generative models. We explore the question of whether conveying information about uncertainty enables programmers to more quickly and accurately produce code when collaborating with an AI-powered code completion tool, and if so, what measure of uncertainty best fits programmers' needs. Through a mixed-methods study with 30 programmers, we compare three conditions: providing the AI system's code completion alone, highlighting tokens with the lowest likelihood of being generated by the underlying generative model, and highlighting tokens with the highest predicted likelihood of being edited by a programmer. We find that highlighting tokens with the highest predicted likelihood of being edited leads to faster task completion and more targeted edits, and is subjectively preferred by study participants. In contrast, highlighting tokens according to their probability of being generated does not provide any benefit over the baseline with no highlighting. We further explore the design space of how to convey uncertainty in AI-powered code completion tools, and find that programmers prefer highlights that are granular, informative, interpretable, and not overwhelming.

Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanations

AI explanations are often mentioned as a way to improve human-AI decision-making. Yet, empirical studies have not found consistent evidence of explanations' effectiveness and, on the contrary, suggest that they can increase overreliance when the AI system is wrong. While many factors may affect reliance on AI support, one important factor is how decision-makers reconcile their own intuition -- which may be based on domain knowledge, prior task experience, or pattern recognition -- with the information provided by the AI system to determine when to override AI predictions. We conduct a think-aloud, mixed-methods study with two explanation types (feature- and example-based) for two prediction tasks to explore how decision-makers' intuition affects their use of AI predictions and explanations, and ultimately their choice of when to rely on AI. Our results identify three types of intuition involved in reasoning about AI predictions and explanations: intuition about the task outcome, features, and AI limitations. Building on these, we summarize three observed pathways for decision-makers to apply their own intuition and override AI predictions. We use these pathways to explain why (1) the feature-based explanations we used did not improve participants' decision outcomes and increased their overreliance on AI, and (2) the example-based explanations we used improved decision-makers' performance over feature-based explanations and helped achieve complementary human-AI performance. Overall, our work identifies directions for further development of AI decision-support systems and explanation methods that help decision-makers effectively apply their intuition to achieve appropriate reliance on AI.

Aligning Offline Metrics and Human Judgments of Value of AI-Pair Programmers

Large language models trained on massive amounts of natural language data and code have shown impressive capabilities in automatic code generation scenarios. Development and evaluation of these models has largely been driven by offline functional correctness metrics, which consider a task to be solved if the generated code passes corresponding unit tests. While functional correctness is clearly an important property of a code generation model, we argue that it may not fully capture what programmers value when collaborating with their AI pair programmers. For example, while a nearly correct suggestion that does not consider edge cases may fail a unit test, it may still provide a substantial starting point or hint to the programmer, thereby reducing total needed effort to complete a coding task. To investigate this, we conduct a user study with (N=49) experienced programmers, and find that while both correctness and effort correlate with value, the association is strongest for effort. We argue that effort should be considered as an important dimension of evaluation in code generation scenarios. We also find that functional correctness remains better at identifying the highest-value generations; but participants still saw considerable value in code that failed unit tests. Conversely, similarity-based metrics are very good at identifying the lowest-value generations among those that fail unit tests. Based on these findings, we propose a simple hybrid metric, which combines functional correctness and similarity-based metrics to capture different dimensions of what programmers might value and show that this hybrid metric more strongly correlates with both value and effort. Our findings emphasize the importance of designing human-centered metrics that capture what programmers need from and value in their AI pair programmers.

Reading Between the Lines: Modeling User Behavior and Costs in AI-Assisted Programming

AI code-recommendation systems (CodeRec), such as Copilot, can assist programmers inside an IDE by suggesting and autocompleting arbitrary code; potentially improving their productivity. To understand how these AI improve programmers in a coding session, we need to understand how they affect programmers' behavior. To make progress, we studied GitHub Copilot, and developed CUPS -- a taxonomy of 12 programmer activities common to AI code completion systems. We then conducted a study with 21 programmers who completed coding tasks and used our labeling tool to retrospectively label their sessions with CUPS. We analyze over 3000 label instances, and visualize the results with timelines and state machines to profile programmer-CodeRec interaction. This reveals novel insights into the distribution and patterns of programmer behavior, as well as inefficiencies and time costs. Finally, we use these insights to inform future interventions to improve AI-assisted programming and human-AI interaction.

Using Machine Translation to Localize Task Oriented NLG Output

One of the challenges in a task oriented natural language application like the Google Assistant, Siri, or Alexa is to localize the output to many languages. This paper explores doing this by applying machine translation to the English output. Using machine translation is very scalable, as it can work with any English output and can handle dynamic text, but otherwise the problem is a poor fit. The required quality bar is close to perfection, the range of sentences is extremely narrow, and the sentences are often very different than the ones in the machine translation training data. This combination of requirements is novel in the field of domain adaptation for machine translation. We are able to reach the required quality bar by building on existing ideas and adding new ones: finetuning on in-domain translations, adding sentences from the Web, adding semantic annotations, and using automatic error detection. The paper shares our approach and results, together with a distillation model to serve the translation models at scale.

Human Evaluation of Spoken vs. Visual Explanations for Open-Domain QA

While research on explaining predictions of open-domain QA systems (ODQA) to users is gaining momentum, most works have failed to evaluate the extent to which explanations improve user trust. While few works evaluate explanations using user studies, they employ settings that may deviate from the end-user's usage in-the-wild: ODQA is most ubiquitous in voice-assistants, yet current research only evaluates explanations using a visual display, and may erroneously extrapolate conclusions about the most performant explanations to other modalities. To alleviate these issues, we conduct user studies that measure whether explanations help users correctly decide when to accept or reject an ODQA system's answer. Unlike prior work, we control for explanation modality, e.g., whether they are communicated to users through a spoken or visual interface, and contrast effectiveness across modalities. Our results show that explanations derived from retrieved evidence passages can outperform strong baselines (calibrated confidence) across modalities but the best explanation strategy in fact changes with the modality. We show common failure cases of current explanations, emphasize end-to-end evaluation of explanations, and caution against evaluating them in proxy modalities that are different from deployment.

Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance

Increasingly, organizations are pairing humans with AI systems to improve decision-making and reducing costs. Proponents of human-centered AI argue that team performance can even further improve when the AI model explains its recommendations. However, a careful analysis of existing literature reveals that prior studies observed improvements due to explanations only when the AI, alone, outperformed both the human and the best human-AI team. This raises an important question: can explanations lead to complementary performance, i.e., with accuracy higher than both the human and the AI working alone? We address this question by devising comprehensive studies on human-AI teaming, where participants solve a task with help from an AI system without explanations and from one with varying types of AI explanation support. We carefully controlled to ensure comparable human and AI accuracy across experiments on three NLP datasets (two for sentiment analysis and one for question answering). While we found complementary improvements from AI augmentation, they were not increased by state-of-the-art explanations compared to simpler strategies, such as displaying the AI's confidence. We show that explanations increase the chance that humans will accept the AI's recommendation regardless of whether the AI is correct. While this clarifies the gains in team performance from explanations in prior work, it poses new challenges for human-centered AI: how can we best design systems to produce complementary performance? Can we develop explanatory approaches that help humans decide whether and when to trust AI input?