NatBDI: Combining BDI reasoning and natural language inference for autonomous agents

Developing autonomous agents to deal with real-world problems is challenging, especially when developers are not necessarily specialists in artificial intelligence. Recent advances in machine learning for natural language processing tasks are reaching performance levels suitable for practical applications, although these approaches rely on opaque, inscrutable models. This poses three key challenges: the interface between the programming and the developer, the efficiency of the resulting agents, and the scrutiny of their behaviour. We tackle the challenge of developing autonomous agents over natural language environments in an efficient agent architecture that leverages recent developments in natural language processing and the intuitive folk psychology abstraction of the beliefs, desires, intentions (BDI) architecture. This paper introduces NatBDI , a new class of agent architecture that uses the BDI reasoning cycle with components driven by natural language processing. This allows a developer to instruct the agent more directly using a combination of controlled natural language structure and natural language knowledge as its programming interface. The resulting architecture handles natural language environments using a combination of language models and natural language inference to bootstrap the agent’s reasoning. We empirically assess the efficiency gains of this combination while introducing a more intuitively programmed autonomous agent. Instructions in this interface substantially improve agent performance in the experimental scenario over a baseline agent created using a pure machine learning approach. The resulting architecture shows that combining learned policies with intuitively engineered domain knowledge yields substantial performance gains. We expect this class of agents to provide a powerful, yet intuitive, tool for agent-driven programming.

Authors

Institutions

Publication Details

Journal
Autonomous Agents and Multi-Agent Systems
Published
2026-11-18
DOI
https://doi.org/10.1007/s10458-026-09781-5
Primary Topic
Multi-Agent Systems and Negotiation
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

NatBDI: Combining BDI reasoning and natural language inference for autonomous agents

Alexandre Yukio Ichida, Rafael Cauê Cardoso, Felipe Meneguzzi
Autonomous Agents and Multi-Agent Systems
Multi-Agent Systems and Negotiation
article

NatBDI: Combining BDI reasoning and natural language inference for autonomous agents

Alexandre Yukio Ichida, Rafael Cauê Cardoso, Felipe Meneguzzi
article en

Abstract

Developing autonomous agents to deal with real-world problems is challenging, especially when developers are not necessarily specialists in artificial intelligence. Recent advances in machine learning for natural language processing tasks are reaching performance levels suitable for practical applications, although these approaches rely on opaque, inscrutable models. This poses three key challenges: the interface between the programming and the developer, the efficiency of the resulting agents, and the scrutiny of their behaviour. We tackle the challenge of developing autonomous agents over natural language environments in an efficient agent architecture that leverages recent developments in natural language processing and the intuitive folk psychology abstraction of the beliefs, desires, intentions (BDI) architecture. This paper introduces NatBDI , a new class of agent architecture that uses the BDI reasoning cycle with components driven by natural language processing. This allows a developer to instruct the agent more directly using a combination of controlled natural language structure and natural language knowledge as its programming interface. The resulting architecture handles natural language environments using a combination of language models and natural language inference to bootstrap the agent’s reasoning. We empirically assess the efficiency gains of this combination while introducing a more intuitively programmed autonomous agent. Instructions in this interface substantially improve agent performance in the experimental scenario over a baseline agent created using a pure machine learning approach. The resulting architecture shows that combining learned policies with intuitively engineered domain knowledge yields substantial performance gains. We expect this class of agents to provide a powerful, yet intuitive, tool for agent-driven programming.

Autonomous Agents and Multi-Agent SystemsVol. 40(2)
University of Aberdeen (GB), Pontifícia Universidade Católica do Rio Grande do Sul (BR)
Pontifícia Universidade Católica do Rio Grande do Sul
Multi-Agent Systems and Negotiation
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon