MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations by @vardhandongre.bsky.social Chi Gui, Hooshang Nayyeri, Shubham Garg, @gokhantur.bsky.social, @dilekh.bsky.social, Vikram Adve

Read more here: mirage-benchmark.github.io

2FA/Duo

Our post examines key concepts, research trends, and the challenges ahead for Embodied Conversational AI. #ConversationalAI (2/2)

Blog: tinyurl.com/embodiedconvai

New Blog Alert: The Future of Human-Robot Conversation! We explore the evolution of embodied conversational agents beyond simple command followers. How will robots develop theory of mind, natural turn-taking, and truly understand human intentions? 🤖💬 #EmbodiedAI #HRI (1/2)

Introducing positive friction in goal-oriented dialogues boosts task success and efficiency! 🎯By strategically slowing down to ask, reveal, or pause, agents improve their understanding of user goals—leading to more efficient, aligned interactions. Read more below:

Will you be making your lectures public by any chance?

👋

Context management is critical when working with Agents. Find out how effective context management transforms conversational web agents! 📄 Our work shows how longer interaction histories and optimized state representation boost agent performance in unseen scenarios.
Poster: tinyurl.com/2yx23tk6

Attending NeurIPS 2024? Learn about simulating users for embodied agents!
Catch our work, "Simulating User Agents for Embodied Conversational AI," at the Open World Agents Workshop on Dec 15.
Poster: tinyurl.com/yc42h4ud
Audio: tinyurl.com/mr2hd35a
@dilekh.bsky.social @gokhantur.bsky.social

Vardhan Dongre, Xiaocheng Yang, Emre Can Acikgoz, Suvodip Dey, Gokhan Tur, Dilek Hakkani-T\"ur
ReSpAct: Harmonizing Reasoning, Speaking, and Acting Towards Building Large Language Model-Based Conversational AI Agents
https://arxiv.org/abs/2411.00927