OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models
Adam Coscia, Shunan Guo, Eunyee Koh, Alex Endert
2025年份
6被引次数
3顶会引用
摘要
Visual highlighting and tracking of real-time feedback on goal progress, with inline explanations of LLM-assisted evaluations A Progress panel Visually review goal progress and evaluation history, as well as manually control goals by locking & completing them B Goal Pipeline User directly controls when their goals are inferred, merged, and evaluated C Figure 1: OnGoal tracks and visualizes conversational goals such as requests and suggestions in multi-turn dialogue with LLMs, helping users better evaluate and review their goal progress.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
引用它的顶会 Paper3
- "Do I Trust the AI?" Towards Trustworthy AI-Assisted Diagnosis: Understanding User Perception in LLM-Supported Clinical ReasoningYuansong Xu, Yichao Zhu, Haokai Wang, Yuchen Wu 等CHI 2026 · 被引用 1 次
- When Should Users Check? Modeling Confirmation Frequency in Multi-Step Agentic AI TasksJieyu Zhou, Aryan Roy, Sneh Gupta, Daniel Weitekamp III 等CHI 2026 · 被引用 1 次
- Nudging Attention to Workplace Meeting Goals: A Large-Scale, Preregistered Field ExperimentLev Tankelevitch, Ava Elizabeth Scott, Nagaravind Challakere, Payod Panda 等CHI 2026 · 被引用 1 次
它引用的顶会 Paper17
- Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsJason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma 等NeurIPS 2022 · 被引用 22,562 次
- Large Language Models Can Be Easily Distracted by Irrelevant ContextFreda Shi, Xinyun Chen, Kanishka Misra, Nathan Scales 等ICML 2023 · 被引用 970 次
- Why Johnny Can't Prompt: How Non-AI Experts Try (and Fail) to Design LLM PromptsJ. D. Zamfirescu-Pereira, Richmond Y. Wong, Bjoern Hartmann, Qian YangCHI 2023 · 被引用 892 次
- The Impact of Generative AI on Critical Thinking: Self-Reported Reductions in Cognitive Effort and Confidence Effects From a Survey of Knowledge WorkersHao-Ping (Hank) Lee, Advait Sarkar, Lev Tankelevitch, Ian Drosos 等CHI 2025 · 被引用 690 次
- The Metacognitive Demands and Opportunities of Generative AILev Tankelevitch, Viktor Kewenig, Auste Simkute, Ava Elizabeth Scott 等CHI 2024 · 被引用 279 次
相关 Paper
- ProgressLM: Towards Progress Reasoning in Vision-Language ModelsJianshu Zhang, Chengxuan Qian, Haosen Sun, Haoran Lu 等ACL 2026 · 被引用 7 次
- A Behavioural and Representational Evaluation of Goal-Directedness in Language Model AgentsRaghu Arghal, Fade Chen, Niall Dalton, Evgenii Kortukov 等ICML 2026
- MAGELLAN: Metacognitive predictions of learning progress guide autotelic LLM agents in large goal spacesLoris Gaven, Thomas Carta, Clément Romac, Cédric Colas 等ICML 2025
- DuetUI: A Bidirectional Context Loop for Human-Agent Co-Generation of Task-Oriented InterfacesYuan Xu, Shaowen Xiang, Yizhi Song, Ruoting Sun 等CHI 2026 · 被引用 2 次
- Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RLJoey Hong, Anca D. Dragan, Sergey LevineNeurIPS 2025 · 被引用 11 次
