paper-with-me

Papers

Agents Thinking Fast and Slow: A Talker-Reasoner Architecture

2024-10-10 · Konstantina Christakopoulou, Shibl Mourad, Maja Matarić

Large language models have enabled agents of all kinds to interact with users through natural conversation. Consequently, agents now have two jobs: conversing and planning/reasoning. Their conversational responses must be informed by all available information, and their actions must help to achieve goals. This dichotomy between conversing with the user and doing multi-step reasoning and planning can be seen as analogous to the human systems of "thinking fast and slow" as introduced by Kahneman. Our approach is comprised of a "Talker" agent (System 1) that is fast and intuitive, and tasked with synthesizing the conversational response; and a "Reasoner" agent (System 2) that is slower, more deliberative, and more logical, and is tasked with multi-step reasoning and planning, calling tools, performing actions in the world, and thereby producing the new agent state. We describe the new Talker-Reasoner architecture and discuss its advantages, including modularity and decreased latency. We ground the discussion in the context of a sleep coaching agent, in order to demonstrate real-world relevance.

📄 PDF Abstract BibTeX arXiv:2410.08328

Code (1)

phunterlau/paper_without_code/tree/main/examples/talker-reasoner pytorch

Similar Papers 제목 키워드 기반

Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents

2025-11-10 · Vidya Srinivas, Zachary Englhardt, Vikram Iyer, Shwetak Patel arxiv

Voice agents face a fundamental tension: the reasoning, retrieval, and tool use that make foundation models capable are iterative and slow, while conversational interaction demands responses on a millisecond timescale. S…

Adaptive Dual Reasoner: Large Reasoning Models Can Think Efficiently by Hybrid Reasoning

2025-10-11 · Yujian Zhang, Keyu Chen, Zhifeng Shen, Ruizhi Qiao 외 arxiv

Although Long Reasoning Models (LRMs) have achieved superior performance on various reasoning scenarios, they often suffer from increased computational costs and inference latency caused by overthinking. To address these…

Reinforcement LearningMathematical Reasoning

Step Back to Leap Forward: Self-Backtracking for Boosting Reasoning of Language Models

2025-02-06 · Xiao-Wen Yang, Xuan-Yi Zhu, Wen-Da Wei, Ding-Chu Zhang 외

The integration of slow-thinking mechanisms into large language models (LLMs) offers a promising way toward achieving Level 2 AGI Reasoners, as exemplified by systems like OpenAI's o1. However, several significant challe…

ProxyThinker: Test-Time Guidance through Small Visual Reasoners

2025-05-30 · Zilin Xiao, Jaywon Koo, Siru Ouyang, Jefferson Hernandez 외

Recent advancements in reinforcement learning with verifiable rewards have pushed the boundaries of the visual reasoning capabilities in large vision-language models (LVLMs). However, training LVLMs with reinforcement fi…

Visual Reasoning

Can Slow-thinking LLMs Reason Over Time? Empirical Studies in Time Series Forecasting

2025-05-30 · Jiahao Wang, Mingyue Cheng, Qi Liu

Time series forecasting (TSF) is a fundamental and widely studied task, spanning methods from classical statistical approaches to modern deep learning and multimodal language modeling. Despite their effectiveness, these …

Language ModelingLanguage ModellingTime SeriesTime Series Forecasting