ACE: Abstractions for Communicating Efficiently

2024-09-30

arXiv.org

AI Summary

AI agents struggle to autonomously develop and evolve communication abstractions in collaborative tasks; existing approaches rely on unrealistic assumptions about abstraction generation and acquisition, whereas humans achieve efficient, compressed linguistic expression through progressive abstraction. Method: We propose PACE, a neuro-symbolic framework integrating programmable symbolic library learning with bandit-regulated reinforcement learning, enabling agents to spontaneously compress instructions and co-construct transferable, shared languages during interaction. Results: In a block-building collaboration task, PACE is the first to replicate human-level abstraction evolution: instruction length decreases significantly, inter-turn language compression persists across episodes, and communication efficiency improves markedly. Contribution: PACE breaks the paradigm requiring pre-specified or supervised abstractions, achieving end-to-end, self-organized, efficient collaborative language evolution—demonstrating autonomous emergence of compositional, reusable communication structures without external linguistic priors.

Technology Category

• Multiagent Systems: Agent Communication
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

A central but unresolved aspect of problem-solving in AI is the capability to introduce and use abstractions, something humans excel at. Work in cognitive science has demonstrated that humans tend towards higher levels of abstraction when engaged in collaborative task-oriented communication, enabling gradually shorter and more information-efficient utterances. Several computational methods have attempted to replicate this phenomenon, but all make unrealistic simplifying assumptions about how abstractions are introduced and learned. Our method, Procedural Abstractions for Communicating Efficiently (PACE), overcomes these limitations through a neuro-symbolic approach. On the symbolic side, we draw on work from library learning for proposing abstractions. We combine this with neural methods for communication and reinforcement learning, via a novel use of bandit algorithms for controlling the exploration and exploitation trade-off in introducing new abstractions. PACE exhibits similar tendencies to humans on a collaborative construction task from the cognitive science literature, where one agent (the architect) instructs the other (the builder) to reconstruct a scene of block-buildings. PACE results in the emergence of an efficient language as a by-product of collaborative communication. Beyond providing mechanistic insights into human communication, our work serves as a first step to providing conversational agents with the ability for human-like communicative abstractions.

Problem

• AI's abstraction capability in problem-solving
• Efficient communication through procedural abstractions
• Neuro-symbolic approach for collaborative task communication

Innovation

• neuro-symbolic approach
• library learning abstractions
• bandit algorithms exploration