Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Qwen-AgentWorld: Language World Models for General Agents

arxiv.org

Post reply on HN
Print view View original

31–40 of 65 posts

Re: Qwen-AgentWorld: Language World Models for General Agents

#31

Post by walrus01 »

Xx_crazy420_xX wrote: post #23

I think open-ended simulation for agents will be a key component for training and planning. Similar as human dreams simulate different scenarios in our head. Biggest challenge will be simulating more abstract and complex systems. Few months ago I did experiment with an open-ended world simulation for AI agent, where the simulated world was progressively building itself based on each of agent actions in open-ended man…

Out of curiosity would you be willing to share the full system prompt for the agent in question described in this test?

Re: Qwen-AgentWorld: Language World Models for General Agents

#32

Post by dofm »

Xx_crazy420_xX wrote: post #23

I think open-ended simulation for agents will be a key component for training and planning. Similar as human dreams simulate different scenarios in our head. Biggest challenge will be simulating more abstract and complex systems. Few months ago I did experiment with an open-ended world simulation for AI agent, where the simulated world was progressively building itself based on each of agent actions in open-ended man…

Is there much evidence we use dreams to pre-emptively simulate scenarios?

Dreaming seems much more likely to be neurological tidying and emotional reprocessing. Helpful for identifying and surfacing long term subconscious needs but not for planning.

My dreams would be precisely useless for making plans from, unless those plans were to involve being caught in public wrapped only in a towel. And even then, I'm not sure they'd be particularly helpful.

Re: Qwen-AgentWorld: Language World Models for General Agents

#34

Post by claud_ia »

dippogriff wrote: post #9

I'm a fan of this direction. For me the most interesting use case for these world models isn't even training, it's verification. If this thing or some idealized version of it can actually reliably simulate state transitions, could you use it to verify an agent's execution path against hard constraints and replace/eclipse LLMs-as-a-judge?

[flagged]

Re: Qwen-AgentWorld: Language World Models for General Agents

#35

Post by npodbielski »

adrian_b wrote: post #17

The smaller of the two models is open weights and available on Huggingface: https://huggingface.co/Qwen/Qwen-AgentWorld-35B-A3B

I tried to run it but seems like it is either broken or it does not work on dockerized llama.cpp:

0.01.865.326 E llama_model_load: error loading model: missing tensor 'blk.40.attn_norm.weight'

Re: Qwen-AgentWorld: Language World Models for General Agents

#36

Post by algoth1 »

dofm wrote: post #32
Xx_crazy420_xX wrote: post #23

I think open-ended simulation for agents will be a key component for training and planning. Similar as human dreams simulate different scenarios in our head. Biggest challenge will be simulating more abstract and complex systems. Few months ago I did experiment with an open-ended world simulation for AI agent, where the simulated world was progressively building itself based on each of agent actions in open-ended man…

Is there much evidence we use dreams to pre-emptively simulate scenarios? Dreaming seems much more likely to be neurological tidying and emotional reprocessing. Helpful for identifying and surfacing long term subconscious needs but not for planning. My dreams would be precisely useless for making plans from, unless those plans were to involve being caught in public wrapped only in a towel. And even then, I'm not sure…

There’s an hypothesis that states we dream so we don’t lose visual processing neural connections. Similar to what happens in blind people: visual processing neurons are recruited to other sensory tasks due to lack of stimulation. My ed. guess is that dreaming probably serves multiple purposes

Re: Qwen-AgentWorld: Language World Models for General Agents

#37

Post by Xx_crazy420_xX »

walrus01 wrote: post #31
Xx_crazy420_xX wrote: post #23

I think open-ended simulation for agents will be a key component for training and planning. Similar as human dreams simulate different scenarios in our head. Biggest challenge will be simulating more abstract and complex systems. Few months ago I did experiment with an open-ended world simulation for AI agent, where the simulated world was progressively building itself based on each of agent actions in open-ended man…

Out of curiosity would you be willing to share the full system prompt for the agent in question described in this test?

sure: https://github.com/Srakai/bench-evolve/blob/76677b5066bafbab...

Re: Qwen-AgentWorld: Language World Models for General Agents

#38

Post by Xx_crazy420_xX »

dofm wrote: post #32
Xx_crazy420_xX wrote: post #23

I think open-ended simulation for agents will be a key component for training and planning. Similar as human dreams simulate different scenarios in our head. Biggest challenge will be simulating more abstract and complex systems. Few months ago I did experiment with an open-ended world simulation for AI agent, where the simulated world was progressively building itself based on each of agent actions in open-ended man…

Is there much evidence we use dreams to pre-emptively simulate scenarios? Dreaming seems much more likely to be neurological tidying and emotional reprocessing. Helpful for identifying and surfacing long term subconscious needs but not for planning. My dreams would be precisely useless for making plans from, unless those plans were to involve being caught in public wrapped only in a towel. And even then, I'm not sure…

I agree, for me it dreaming was always reprocessing. The resimulation of scenarios part i mentioned can be over-assumption and it might be wrong. One thing i noticed is that sometimes i reprocess motoric movements after martial arts lessons, that was my main clue.

Re: Qwen-AgentWorld: Language World Models for General Agents

#40

Post by Xx_crazy420_xX »

avaer wrote: post #27
Xx_crazy420_xX wrote: post #23

I think open-ended simulation for agents will be a key component for training and planning. Similar as human dreams simulate different scenarios in our head. Biggest challenge will be simulating more abstract and complex systems. Few months ago I did experiment with an open-ended world simulation for AI agent, where the simulated world was progressively building itself based on each of agent actions in open-ended man…

I agree; after running out of data on the internet, and humans being too slow to generate data, simulation is the only frontier left for improving things (training, datasets, reasoning). And it's probably the most ethical one too. If nothing else I'm glad to see "world models" that are actually modeling some kind of worlds, instead of the term being applied as a hype layer for video/splats diffusion.

Physical simulations seem like next step, but how do you simulate dynamics in complex systems im not sure. Stock market is a good example with many trying to simulate that, but at the end you have to make some tradeoffs in terms of abstraction level you are simulating.

For social backed simulations i guess some kind of grounding will be needed based on real examples, but then the out of distribution cases will need an other solution. As rate of changes in our civilization increases, the out of distribution cases will be more and more prominent.

Post reply on HN