Good read. Currently there are lot of issues in autonomous agents apart from Finite context length, task decomposition and natural language as interface mentioned in the article.
I think for agents to truly find adoption in real world, agent trajectory fine tuning is critical component - how do you make an agent perform better to achieve particular objective with every subsequent run. Basically making the agents learn similar to how we learn when we<p>Also I think current LLMs might not fit well for agent use cases in mid to long term because the RL they go through is based on input-best output methods whereas the intelligence that you need in agents is more around how to build an algorithm to achieve an objective on the fly - this requires perhaps new type of large models ( Large Agent Models ? ) which are trained using RLfD ( Reinforcement Learning from demonstration )<p>Also I think one of the key missing piece is a highly configurable software middle ware between Intelligence ( LLMs ), Memory ( Vector Dbs ~LTMs, STMs ), Tools and workflows across every iteration. Current agent core loop to find next best action is too simplistic. For example if core self prompting loop or iteration of an agent can be configured for the use case in hand. Eg for BabyAGI, every iteration goes through workflow of Plan, Prioritize and Execute or in AutoGPT it finds the next best action based on LTM/STM, or GPTEngineer it is to write specs > write tests > write code. Now for dev infra monitoring agent this workflow might be totally different - it would look like consume logs from different tools like Grafana, Splunk, APMs > See if it doesnt have an anomaly > if it has an anomaly then take human input for feedback. Every use case in real world has it's own workflow and current construct of agent frameworks have this thing hard coded in base prompt. In SuperAGI( <a href="https://superagi.com" rel="nofollow noreferrer">https://superagi.com</a>) ( disclaimer : Im creator of it ), core iteration workflow of agent can be defined as part of agent provisioning.<p>Another missing piece is notion of Knowledge. Agents currently depend entirely upon knowledge of LLMs or search results to execute on tasks, but if a specialised knowledge set is plugged to an agent, it performs significantly better.