AI Agents

This cluster discusses AI agents, including generative agents, multi-agent systems, agentic frameworks, simulations, and related research like generative agents in RPG towns or production agentic systems.

➡️ Stable 1.4x AI & Machine Learning
2,675
Comments
20
Years Active
5
Top Authors
#1898
Topic ID

Activity Over Time

2007
4
2008
7
2009
20
2010
24
2011
27
2012
24
2013
39
2014
40
2015
49
2016
104
2017
143
2018
94
2019
124
2020
102
2021
108
2022
167
2023
433
2024
362
2025
717
2026
93

Keywords

AgeLab LLM MIT AIXI MVP A2A googleblog.com AI ACT IMO agents ai agent models model rl mcp llm ai models ais

Sample Comments

edoceo Mar 1, 2025 View on HN

Like make a feedback loop? Agent/Actor type of play? Maybe test against an AI formed thesis even?

arc619 Apr 29, 2023 View on HN

What you describe sounds like experiments with "generative agents".Check out https://arxiv.org/abs/2304.03442

neuronexmachina May 27, 2023 View on HN

Something like this? https://arstechnica.com/information-technology/2023/04/surpr...

Grimblewald May 9, 2024 View on HN

Check out you.com genuius mode, it does internal dialogue of sorts, which you can open up and explore. The same is true for many "agent" based systems. It turns out giving LLMs the ability to talk through problems with themsleves massivly improves their abilities. Same as using chain of thought prompting.

kojiwakayama Dec 14, 2024 View on HN

Interesting. Are you thinking of an agentic system here?

milliondreams Apr 2, 2024 View on HN

Looks promising approach to Agentic AI systems.

IanCal Mar 1, 2023 View on HN

You might be interested in this: https://www.adept.ai/blog/act-1

zaphirplane Aug 7, 2025 View on HN

Is there a better agent than the anthropic one

joaomdmoura Jan 2, 2024 View on HN

Cutting-edge framework for orchestrating role-playing, autonomous AI agents. By fostering collaborative intelligence, CrewAI empowers agents to work together seamlessly, tackling complex tasks.

Demiurge Oct 24, 2025 View on HN

That's a good example, yes. I think this one can actually be interpreted by multiple AI agents to do search on the algorithms, or could even train a model, and then run the model. How amazing would it be, if this could actually all happen based on a few prompts :)