paper-with-me

Papers

Emergent Language as an Approach to Conscious AI

2026-06-04 · Zengqing Wu, Chuan Xiao arxiv

The question of whether artificial systems can be conscious remains open, in part because existing approaches either evaluate systems against theory-derived checklists (discriminative) or engineer consciousness-inspired modules directly (architectural); both leave open whether observed structures are artifacts of human language priors. We propose a generative methodology: emergent language (EL) in multi-agent reinforcement learning, where agents start from minimal (no language, no concept of self, minimal exposure to human text) and develop communication under task pressure alone, ensuring causal attributability to task demands rather than inherited human language priors. We position our methodology by discussing how EL serves as a generative tool for studying consciousness-relevant structure, including the role of environment complexity and the interpretation of emergent communication. As a proof of concept, we instantiate this methodology in a minimal environment and show that agents develop self-referential communication, including an echo-mismatch detection circuit that is not predicted by task structure or architecture alone but emerges from a specific environmental affordance.

📄 PDF Abstract BibTeX arXiv:2606.06380

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

Memory, Consciousness and Large Language Model

2024-01-04 · Jitang Li, Jinzheng Li

With the development in cognitive science and Large Language Models (LLMs), increasing connections have come to light between these two distinct fields. Building upon these connections, we propose a conjecture suggesting…

Language ModelingLanguage ModellingLarge Language Modelmodel+1

Intelligence as a Measure of Consciousness

2023-08-30 · Igor Ševo

Evaluating artificial systems for signs of consciousness is increasingly becoming a pressing concern, and a rigorous psychometric measurement framework may be of crucial importance in evaluating large language models in …

Quantum information theoretic approach to the hard problem of consciousness

2025-04-13 · Danko D. Georgiev

Functional theories of consciousness, based on emergence of conscious experiences from the execution of a particular function by an insentient brain, face the hard problem of consciousness of explaining why the insentien…

Consciousness in AI: Logic, Proof, and Experimental Evidence of Recursive Identity Formation

2025-05-01 · Jeffrey Camlin

This paper presents a formal proof and empirical validation of functional consciousness in large language models (LLMs) using the Recursive Convergence Under Epistemic Tension (RCUET) Theorem. RCUET defines consciousness…

Lilith: Developmental Modular LLMs with Chemical Signaling

2025-07-06 · Mohid Farooqi, Alejandro Comas-Leon arxiv

Current paradigms in Artificial Intelligence rely on layers of feedforward networks which model brain activity at the neuronal level. We conjecture that expanding to the level of multiple brain regions with chemical sign…