541 citations · 791 across the 14 of their papers we have counts for
10 papers · 1 filter
OpaqueToolsBench: Learning Nuances of Tool Behavior Through Interaction
Skyler Hallinan, Thejas Venkatesh, Xiang Ren +4
Tool-calling is essential for Large Language Model (LLM) agents to complete real-world tasks. While most existing benchmarks assume simple, perfectly documented tools, real-world t…
Lost in the Maze: Overcoming Context Limitations in Long-Horizon Agentic Search
Howard Yen, Yoonsang Lee, Ashwin Paranjape +5
Long-horizon agentic search requires iteratively exploring the web over long trajectories and synthesizing information across many sources, enabling powerful applications like deep…
Lost in the Middle: How Language Models Use Long Contexts
Nelson F. Liu, Kevin Lin, John Hewitt +4
While recent language models have the ability to take long contexts as input, relatively little is known about how well they use longer context. We analyze the performance of langu…
Evaluating Human-Language Model Interaction
Mina Lee, Megha Srivastava, Amelia Hardy +15
Many real-world applications of language models (LMs), such as writing assistance and code autocomplete, involve human-LM interaction. However, most benchmarks are non-interactive…
When can I Speak? Predicting initiation points for spoken dialogue agents
Siyan Li, Ashwin Paranjape, Christopher D. Manning
Current spoken dialogue systems initiate their turns after a long period of silence (700-1000ms), which leads to little real-time feedback, sluggish responses, and an overall stilt…
Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent
Ethan A. Chi, Ashwin Paranjape, Abigail See +18
We present Chirpy Cardinal, an open-domain social chatbot. Aiming to be both informative and conversational, our bot chats with users in an authentic, emotionally intelligent way.…