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

61–65 of 65 posts

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

#61

Post by juliangoldsmith »

jvanderbot wrote: post #52
kakugawa wrote: post #22

Earlier quoted context omitted.

Here's the demo: https://docs.qwenlm.ai/resources/mlu56_demo.html Here's the description of the world model prompt for the web domain: "A precise GUI state simulator — given the current screen (as HTML) and a user action, predicts the exact next screen as a complete, self-contained HTML document." (You can click the world model prompt box to expand it and see the full prompt.) So the world model generates the current…

And a world model is useful for ... action space search which would require prediction?

It should improve agents' action selection by allowing them to evaluate actions' effects before performing them.

An agent using only a regular LLM has no real way to predict the results of its actions. It has to just take an action based on its training data and hope it's the right one. With a world model like this, it could do a second pass before each action to catch mistakes.

I don't know if this actually delivers yet, but if it does it might help make agents more usable.

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

#63

Post by jvanderbot »

juliangoldsmith wrote: post #61
jvanderbot wrote: post #52

Earlier quoted context omitted.

And a world model is useful for ... action space search which would require prediction?

It should improve agents' action selection by allowing them to evaluate actions' effects before performing them. An agent using only a regular LLM has no real way to predict the results of its actions. It has to just take an action based on its training data and hope it's the right one. With a world model like this, it could do a second pass before each action to catch mistakes. I don't know if this actually delivers…

Yeah, the fun part is the lookahead search, and here we are back in classical action-space fanout search, except I guess emulated in an LLM

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

#64

Post by khimaros »

walrus01 wrote: post #29
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

Give it a day or two and the 'unsloth' people will probably publish a Q6 and Q8 (maybe Q8XL?) quantization in GGUF format for llama-server and other users.

they have arrived: https://huggingface.co/unsloth/Qwen-AgentWorld-35B-A3B-GGUF

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

#65

Post by npodbielski »

khimaros wrote: post #54
npodbielski wrote: post #35

Earlier quoted context omitted.

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'

that particular quant is just corrupted. these work but seem to loop in reasoning a lot https://huggingface.co/groxaxo/Qwen-AgentWorld-35B-A3B-GGUF

unsloth version works.
Post reply on HN