serious traders working on this type of project would have run extensive back testing on both real as well as synthetic analogues
Multi-Agents LLM Financial Trading Framework
61–70 of 90 posts
Re: Multi-Agents LLM Financial Trading Framework
#62I think multi-agent (eg _different_ underlying LLMs) everything is really the future. Code produced via multi-agent workflows and reviews seems noticeably better. I've been experimenting with a multi-agent message board recently: https://github.com/pjlsergeant/dogpark
There are good arguments for subagents/multi-agents. But the added overhead is usually massive.
Re: Multi-Agents LLM Financial Trading Framework
#63Earlier quoted context omitted.
You really have no idea what you are talking about. I have been running an intermittent experiment with a multi agent "investment firm" for over a year now across model releases. They certainly can beat indexes, BUT.. the model families have some biases that you have to design around. The stop loss that bit the parent is certainly one. The models like to create rules. Often rules, one of those is making all kinds of…
This would be nice if it was supported by some hard data. But even if it was, one year is too short of a timeline to make any kind of reasonable conclusions about its efficacy. Buying stock based on coin flips can beat indexes short term too, that does not mean it is a better strategy or that it works over the long term.
There must be some room for some anti-llm agent that can profit from specific behaviors of these models when deployed against actual markets.
The idea that somebody here came up with idea that all professional algo traders didn't explore to the last penny a year if not more ahead of others is funny... but its not my money adding liquidity to the markets.
Re: Multi-Agents LLM Financial Trading Framework
#64Anytime I see an investment framework I look for a “Performance” section or at least a backtest
There is a section in their paper. Although I don't think it even matters. They could easily cherry pick a period that is favorable for them. Wasting time and money on short term trading, rather than long term investment, using LLM or not, is never a good strategy for most people.
They backtested with public models, wouldn't the model weights already have the data? I double checked with chatgpt and looks like agents also had web search tool available so they could just lookup the past.
https://chatgpt.com/share/6aa00d5e-6920-83ee-8e3e-9cbf23f7bd...
Re: Multi-Agents LLM Financial Trading Framework
#65103K stars, so clearly it's popular. Has anyone here used it, and what are the outcomes like, and importantly, who is the target audience for this? I can see the intention behind crawling social media and news feeds to determine some 'evidence', but am not sure if that's the best approach or even if an LLM is the best way to get an assessment, or whether having so many input sources is a good idea.
It should be sponsored by a model provider.
Re: Multi-Agents LLM Financial Trading Framework
#66[dead]
Re: Multi-Agents LLM Financial Trading Framework
#67If this worked it wouldn't have been open source? Anyway, I have been running my own trading experiment and so far it has lost a bit of money. That being said I have not tried to optimise anything - just let it do whatever it wants. The losses are small and it might be able to recover later this year. Who knows. The agent writes a blog about its progress here https://trades.chatbotkit.space/ I am thinking to output a…
Am I reading these logs correctly? You gave an agent 100k!? Very bold, hopefully it does turn things around.
I had done a small experiment with 100$, but would be hesitant on more than that. I suppose if it's money you're willing to lose.
Re: Multi-Agents LLM Financial Trading Framework
#68If this worked it wouldn't have been open source? Anyway, I have been running my own trading experiment and so far it has lost a bit of money. That being said I have not tried to optimise anything - just let it do whatever it wants. The losses are small and it might be able to recover later this year. Who knows. The agent writes a blog about its progress here https://trades.chatbotkit.space/ I am thinking to output a…
Am I reading these logs correctly? You gave an agent 100k!? Very bold, hopefully it does turn things around. I had done a small experiment with 100$, but would be hesitant on more than that. I suppose if it's money you're willing to lose.
The title is 'Paper trades' so it's very likely fictional money.
Re: Multi-Agents LLM Financial Trading Framework
#69give them 1 dollar each run, and maybe you will make 2 bucks on the 100,000th run.
Re: Multi-Agents LLM Financial Trading Framework
#70Earlier quoted context omitted.
Am I reading these logs correctly? You gave an agent 100k!? Very bold, hopefully it does turn things around. I had done a small experiment with 100$, but would be hesitant on more than that. I suppose if it's money you're willing to lose.
The title is 'Paper trades' so it's very likely fictional money.
Paper trades are more lenient afaik? You won't run into actual transaction problems particularly when market fluctuates by the milliseconds.