SCOOP: A Framework for Proactive Collaboration and Social Continual Learning through Natural Language Interaction andCausal Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ognibene, Dimitri, Patania, Sabrina, Annese, Luca, Koyuturk, Cansu, Garzotto, Franca, Vizzari, Giuseppe, Ruggeri, Azzurra, Colombani, Simone
Format:	Preprint
Published:	2025
Subjects:	Multiagent Systems Human-Computer Interaction Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

_version_	1866915196056895488
author	Ognibene, Dimitri Patania, Sabrina Annese, Luca Koyuturk, Cansu Garzotto, Franca Vizzari, Giuseppe Ruggeri, Azzurra Colombani, Simone
author_facet	Ognibene, Dimitri Patania, Sabrina Annese, Luca Koyuturk, Cansu Garzotto, Franca Vizzari, Giuseppe Ruggeri, Azzurra Colombani, Simone
contents	Multimodal information-gathering settings, where users collaborate with AI in dynamic environments, are increasingly common. These involve complex processes with textual and multimodal interactions, often requiring additional structural information via cost-incurring requests. AI helpers lack access to users' true goals, beliefs, and preferences and struggle to integrate diverse information effectively. We propose a social continual learning framework for causal knowledge acquisition and collaborative decision-making. It focuses on autonomous agents learning through dialogues, question-asking, and interaction in open, partially observable environments. A key component is a natural language oracle that answers the agent's queries about environmental mechanisms and states, refining causal understanding while balancing exploration or learning, and exploitation or knowledge use. Evaluation tasks inspired by developmental psychology emphasize causal reasoning and question-asking skills. They complement benchmarks by assessing the agent's ability to identify knowledge gaps, generate meaningful queries, and incrementally update reasoning. The framework also evaluates how knowledge acquisition costs are amortized across tasks within the same environment. We propose two architectures: 1) a system combining Large Language Models (LLMs) with the ReAct framework and question-generation, and 2) an advanced system with a causal world model, symbolic, graph-based, or subsymbolic, for reasoning and decision-making. The latter builds a causal knowledge graph for efficient inference and adaptability under constraints. Challenges include integrating causal reasoning into ReAct and optimizing exploration and question-asking in error-prone scenarios. Beyond applications, this framework models developmental processes combining causal reasoning, question generation, and social learning.
format	Preprint
id	arxiv_https___arxiv_org_abs_2503_10241
institution	arXiv
publishDate	2025
record_format	arxiv
spellingShingle	SCOOP: A Framework for Proactive Collaboration and Social Continual Learning through Natural Language Interaction andCausal Reasoning Ognibene, Dimitri Patania, Sabrina Annese, Luca Koyuturk, Cansu Garzotto, Franca Vizzari, Giuseppe Ruggeri, Azzurra Colombani, Simone Multiagent Systems Human-Computer Interaction Robotics Multimodal information-gathering settings, where users collaborate with AI in dynamic environments, are increasingly common. These involve complex processes with textual and multimodal interactions, often requiring additional structural information via cost-incurring requests. AI helpers lack access to users' true goals, beliefs, and preferences and struggle to integrate diverse information effectively. We propose a social continual learning framework for causal knowledge acquisition and collaborative decision-making. It focuses on autonomous agents learning through dialogues, question-asking, and interaction in open, partially observable environments. A key component is a natural language oracle that answers the agent's queries about environmental mechanisms and states, refining causal understanding while balancing exploration or learning, and exploitation or knowledge use. Evaluation tasks inspired by developmental psychology emphasize causal reasoning and question-asking skills. They complement benchmarks by assessing the agent's ability to identify knowledge gaps, generate meaningful queries, and incrementally update reasoning. The framework also evaluates how knowledge acquisition costs are amortized across tasks within the same environment. We propose two architectures: 1) a system combining Large Language Models (LLMs) with the ReAct framework and question-generation, and 2) an advanced system with a causal world model, symbolic, graph-based, or subsymbolic, for reasoning and decision-making. The latter builds a causal knowledge graph for efficient inference and adaptability under constraints. Challenges include integrating causal reasoning into ReAct and optimizing exploration and question-asking in error-prone scenarios. Beyond applications, this framework models developmental processes combining causal reasoning, question generation, and social learning.
title	SCOOP: A Framework for Proactive Collaboration and Social Continual Learning through Natural Language Interaction andCausal Reasoning
topic	Multiagent Systems Human-Computer Interaction Robotics
url	https://arxiv.org/abs/2503.10241