James Henderson, Yuta Nagano, Martina Milighetti, and Andreas Tiffeau-Mayer

PNAS 121 (42) e2408696121

The specificity of cellular immune responses is determined by the binding of T cell receptors (TCRs) to diverse ligands, yet due to their vast diversity, most TCRs lack experimentally validated binding partners. To overcome this gap requires understanding the recognition code linking receptors and ligands. Here, we introduce an information theoretic approach to rank TCR features by their relevance to predicting specificity and bound how accurately T cell specificity can be predicted from partial information. By identifying informative features, our work provides a rational basis for prioritizing matches in TCR databases and for developing machine learning models to predict TCR–ligand interactions.

Read the full article at: www.pnas.org

Ryosuke Takata, Atsushi Masumori, Takashi Ikegami

We study the emergence of agency from scratch by using Large Language Model (LLM)-based agents. In previous studies of LLM-based agents, each agent’s characteristics, including personality and memory, have traditionally been predefined. We focused on how individuality, such as behavior, personality, and memory, can be differentiated from an undifferentiated state. The present LLM agents engage in cooperative communication within a group simulation, exchanging context-based messages in natural language. By analyzing this multi-agent simulation, we report valuable new insights into how social norms, cooperation, and personality traits can emerge spontaneously. This paper demonstrates that autonomously interacting LLM-powered agents generate hallucinations and hashtags to sustain communication, which, in turn, increases the diversity of words within their interactions. Each agent’s emotions shift through communication, and as they form communities, the personalities of the agents emerge and evolve accordingly. This computational modeling approach and its findings will provide a new method for analyzing collective artificial intelligence.

Read the full article at: arxiv.org

Sneha Ramshanker, Hungtang Ko, Radhika Nagpal

Robot swarms offer significant potential for inspecting di- verse infrastructure, ranging from bridges to space stations. However, effective inspection requires accurate robot localization, which demands substantial computational resources and limits productivity. Inspired by biological systems, we introduce a novel cooperative localization mech- anism that minimizes collective computation expenditure through self- organized sacrifice. Here, a few agents bear the computational burden of localization; through local interactions, they improve the inspection pro- ductivity of the swarm. Our approach adaptively maximizes inspection productivity for unconstrained trajectories in dynamic interaction and environmental settings. We demonstrate the optimality and robustness using mean-field analytical models, multi-agent simulations, and hard- ware experiments with metal climbing robots inspecting a 3D cylinder.

Read the full article at: ssr.princeton.edu