3 papers
cs.MA2026
Prosociality by Coupling, Not Mere Observation: Homeostatic Sharing in an Inspectable Recurrent Artificial Life Agent
Aishik Sanyal
Artificial agents can be made to ``help'' through explicit social rewards, hard-coded prosocial bonuses, or direct access to another agent's state. I isolate a narrower route: home…
cs.AI2026
ReCoN-Ipsundrum: An Inspectable Recurrent Persistence Loop Agent with Affect-Coupled Control and Mechanism-Linked Consciousness Indicator Assays
Aishik Sanyal
Indicator-based approaches to machine consciousness recommend mechanism-linked evidence triangulated across tasks, supported by architectural inspection and causal intervention. In…
cs.AI2025
Spark: A System for Scientifically Creative Idea Generation
Aishik Sanyal, Samuel Schapiro, Sumuk Shashidhar +3
Recently, large language models (LLMs) have shown promising abilities to generate novel research ideas in science, a direction which coincides with many foundational principles in…