Autonomous agents have long been a research focus in academic and industry communities.Previous research often focuses on training agents with limited knowledge within isolated environments,which diverges significantl...Autonomous agents have long been a research focus in academic and industry communities.Previous research often focuses on training agents with limited knowledge within isolated environments,which diverges significantly from human learning processes,and makes the agents hard to achieve human-like decisions.Recently,through the acquisition of vast amounts of Web knowledge,large language models(LLMs)have shown potential in human-level intelligence,leading to a surge in research on LLM-based autonomous agents.In this paper,we present a comprehensive survey of these studies,delivering a systematic review of LLM-based autonomous agents from a holistic perspective.We first discuss the construction of LLM-based autonomous agents,proposing a unified framework that encompasses much of previous work.Then,we present a overview of the diverse applications of LLM-based autonomous agents in social science,natural science,and engineering.Finally,we delve into the evaluation strategies commonly used for LLM-based autonomous agents.Based on the previous studies,we also present several challenges and future directions in this field.展开更多
Therapeutic proteins have recently received increasing attention because of their clinical potential.Currently,most therapeutic proteins are produced on a large scale using various cell culture systems.However,storing...Therapeutic proteins have recently received increasing attention because of their clinical potential.Currently,most therapeutic proteins are produced on a large scale using various cell culture systems.However,storing and transporting these therapeutic proteins at low temperatures makes their distribution expensive and problematic,especially for applications in remote locations.To this end,an emerging solution is to use point-of-care technologies that enable immediate and accessible protein production at or near the patient’s bedside.Here we present the development of“Therapeutics-On-a-Chip(TOC)”,an integrated microfluidic platform that enables point-of-care synthesis and purification of therapeutic proteins.We used fresh and lyophilized materials for cell-free synthesis of therapeutic proteins on microfluidic chips and applied immunoprecipitation for highly efficient,on-chip protein purification.We first demonstrated this approach by expressing and purifying a reporter protein,green fluorescent protein.Next,we used TOC to produce cecropin B,an antimicrobial peptide that is widely used to control biofilmassociated diseases.We successfully synthesized and purified cecropin B at 63 ng/μl within 6 h with a 92%purity,followed by confirming its antimicrobial functionality using a growth inhibition assay.Our TOC technology provides a new platform for point-of-care production of therapeutic proteins at a clinically relevant quantity.展开更多
基金the National Natural Science Foundation of China(Grant No.62102420)the Beijing Outstanding Young Scientist Program(No.BJJWZYJH012019100020098)。
文摘Autonomous agents have long been a research focus in academic and industry communities.Previous research often focuses on training agents with limited knowledge within isolated environments,which diverges significantly from human learning processes,and makes the agents hard to achieve human-like decisions.Recently,through the acquisition of vast amounts of Web knowledge,large language models(LLMs)have shown potential in human-level intelligence,leading to a surge in research on LLM-based autonomous agents.In this paper,we present a comprehensive survey of these studies,delivering a systematic review of LLM-based autonomous agents from a holistic perspective.We first discuss the construction of LLM-based autonomous agents,proposing a unified framework that encompasses much of previous work.Then,we present a overview of the diverse applications of LLM-based autonomous agents in social science,natural science,and engineering.Finally,we delve into the evaluation strategies commonly used for LLM-based autonomous agents.Based on the previous studies,we also present several challenges and future directions in this field.
文摘Therapeutic proteins have recently received increasing attention because of their clinical potential.Currently,most therapeutic proteins are produced on a large scale using various cell culture systems.However,storing and transporting these therapeutic proteins at low temperatures makes their distribution expensive and problematic,especially for applications in remote locations.To this end,an emerging solution is to use point-of-care technologies that enable immediate and accessible protein production at or near the patient’s bedside.Here we present the development of“Therapeutics-On-a-Chip(TOC)”,an integrated microfluidic platform that enables point-of-care synthesis and purification of therapeutic proteins.We used fresh and lyophilized materials for cell-free synthesis of therapeutic proteins on microfluidic chips and applied immunoprecipitation for highly efficient,on-chip protein purification.We first demonstrated this approach by expressing and purifying a reporter protein,green fluorescent protein.Next,we used TOC to produce cecropin B,an antimicrobial peptide that is widely used to control biofilmassociated diseases.We successfully synthesized and purified cecropin B at 63 ng/μl within 6 h with a 92%purity,followed by confirming its antimicrobial functionality using a growth inhibition assay.Our TOC technology provides a new platform for point-of-care production of therapeutic proteins at a clinically relevant quantity.
