Large Language Models (LLMs) have achieved remarkable success across a wide array of tasks. Due to the impressive planning and reasoning abilities of LLMs, they have been used as autonomous agents to do many tasks automatically. Recently, based on the development of using one LLM as a single planning or decision-making agent, LLM-based multi-agent systems have achieved considerable progress in complex problem-solving and world simulation. To provide the community with an overview of this dynamic field, we present this survey to offer an in-depth discussion on the essential aspects of multi-agent systems based on LLMs, as well as the challenges. Our goal is for readers to gain substantial insights on the following questions: What domains and environments do LLM-based multi-agents simulate? How are these agents profiled and how do they communicate? What mechanisms contribute to the growth of agents' capacities? For those interested in delving into this field of study, we also summarize the commonly used datasets or benchmarks for them to have convenient access. To keep researchers updated on the latest studies, we maintain an open-source GitHub repository, dedicated to outlining the research on LLM-based multi-agent systems.
more »
« less
From Flatland to Jupiter: Searching for Rules of Interaction Across Biological Scales
Synopsis In this future-spanning perspective, we examine how an agent-based model could be used to define general rules for interactions across biological systems and evolutionary time. To date, there have been a number of attempts to simulate the emergence of ecological communities using agent-based models of individuals that have evolving traits. Here we speculate whether it is possible to use this computational modeling to simulate self-organizing systems and, importantly, to decipher universal principles that govern biological interactions. This perspective is a thought exercise, meant to extrapolate from current knowledge to how we may make Jupiter-shot leaps to further advance the biosciences in the 21st century.
more »
« less
- Award ID(s):
- 1656626
- NSF-PAR ID:
- 10322042
- Date Published:
- Journal Name:
- Integrative and Comparative Biology
- Volume:
- 61
- Issue:
- 6
- ISSN:
- 1540-7063
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Self-organized pattern behavior is ubiquitous throughout nature, from fish schooling to collective cell dynamics during organism development. Qualitatively these patterns display impressive consistency, yet variability inevitably exists within pattern-forming systems on both microscopic and macroscopic scales. Quantifying variability and measuring pattern features can inform the underlying agent interactions and allow for predictive analyses. Nevertheless, current methods for analyzing patterns that arise from collective behavior capture only macroscopic features or rely on either manual inspection or smoothing algorithms that lose the underlying agent-based nature of the data. Here we introduce methods based on topological data analysis and interpretable machine learning for quantifying both agent-level features and global pattern attributes on a large scale. Because the zebrafish is a model organism for skin pattern formation, we focus specifically on analyzing its skin patterns as a means of illustrating our approach. Using a recent agent-based model, we simulate thousands of wild-type and mutant zebrafish patterns and apply our methodology to better understand pattern variability in zebrafish. Our methodology is able to quantify the differential impact of stochasticity in cell interactions on wild-type and mutant patterns, and we use our methods to predict stripe and spot statistics as a function of varying cellular communication. Our work provides an approach to automatically quantifying biological patterns and analyzing agent-based dynamics so that we can now answer critical questions in pattern formation at a much larger scale.more » « less
-
more » « less
Abstract An agent‐based perspective in the study of complex systems is well established in diverse disciplines, yet is only beginning to be applied to evolutionary developmental biology. In this essay, we begin by defining agency and associated terminology formally. We then explore the assumptions and predictions of an agency perspective, apply these to select processes and key concept areas relevant to practitioners of evolutionary developmental biology, and consider the potential epistemic roles that an agency perspective might play in evo devo. Throughout, we discuss evidence supportive of agential dynamics in biological systems relevant to evo devo and explore where agency thinking may enrich the explanatory reach of research efforts in evolutionary developmental biology.
-
Agent-based models provide a flexible framework that is frequently used for modelling many biological systems, including cell migration, molecular dynamics, ecology and epidemiology. Analysis of the model dynamics can be challenging due to their inherent stochasticity and heavy computational requirements. Common approaches to the analysis of agent-based models include extensive Monte Carlo simulation of the model or the derivation of coarse-grained differential equation models to predict the expected or averaged output from the agent-based model. Both of these approaches have limitations, however, as extensive computation of complex agent-based models may be infeasible, and coarse-grained differential equation models can fail to accurately describe model dynamics in certain parameter regimes. We propose that methods from the equation learning field provide a promising, novel and unifying approach for agent-based model analysis. Equation learning is a recent field of research from data science that aims to infer differential equation models directly from data. We use this tutorial to review how methods from equation learning can be used to learn differential equation models from agent-based model simulations. We demonstrate that this framework is easy to use, requires few model simulations, and accurately predicts model dynamics in parameter regions where coarse-grained differential equation models fail to do so. We highlight these advantages through several case studies involving two agent-based models that are broadly applicable to biological phenomena: a birth–death–migration model commonly used to explore cell biology experiments and a susceptible–infected–recovered model of infectious disease spread.more » « less
-
more » « less
Abstract Classical hydrogen bonds have, for many decades, been the dominant non‐covalent interaction in the toolbox that chemists and chemical engineers have used to design and control the structures of compounds and molecular assemblies as novel materials. Recently, a set of non‐classical non‐covalent (NC−NC) interactions have emerged that exploit the properties of the Group IV, V, VI, and VII elements of the periodic table (the tetrel, pnictogen, chalcogen, and halogen bonds, respectively). Our research group has been characterizing the prevalence, geometric constraints, and structure‐function relationship specifically of the halogen bond in biological systems. We have been particularly interested in exploiting the biological halogen bonds (or BXBs) to control the structures, stabilities, and activities of biomolecules, including the DNA Holliday junction and enzymes. In this review, we first provide a set of criteria for how to determine whether BXBs or any other NC−NC interactions would have biological relevance. We then navigate the trail of studies that had led us from an initial, very biological question to our current point in the journey to establish BXBs as a tool for biomolecular engineering. Finally, we close with a perspective on future directions for this line of research.
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1093/icb/icab159
