corpus.blog
54,302 blogs · 4,481,250 posts Claim your blog
Record · corpus.blog/posts/01a0df50-42a2-7315-a56c-0dc7befd0d1e

Agentic World Models

cameronrwolfe.substack.com · published 20 July 2026

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at cameronrwolfe.substack.com Wayback capture
0blogs citing
First cited
—
Most recent
—
Rank this month
not ranked
Links from this post
108
Words captured
12,560

Cited by

No blog we hold has cited this post yet.

Links from this post

Link
Host
https://substackcdn.com/image/fetch/$s_!sB7Z!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fdf7d43db-ccee-4028-82a7-ad73fd5f6d56_2496x1404.png
substackcdn.com
The data black hole at the center of AI Read at the source ↗
dwarkesh.com
Agentic RL: Frameworks and Best Practices Read at the source ↗
cameronrwolfe.substack.com
https://substackcdn.com/image/fetch/$s_!rWp9!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fff9acf96-b011-49ad-a723-8da26eed9136_1298x1060.png
substackcdn.com
https://docs.pytorch.org/docs/2.13/generated/torch.nn.functional.cross_entropy.html
docs.pytorch.org
https://sebastianraschka.com/faq/docs/negative-log-likelihood-logistic-loss.html
sebastianraschka.com
https://substackcdn.com/image/fetch/$s_!B2CU!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fdadeadad-f9e1-4f32-906a-e7dd36ef4c80_1306x690.png
substackcdn.com
https://huggingface.co/datasets/tatsu-lab/alpaca
huggingface.co
http://huggingface.co/commoncrawl
huggingface.co
https://sebastianraschka.com/faq/docs/causal-attention.html
sebastianraschka.com
https://cameronrwolfe.substack.com/p/decoder-only-transformers-the-workhorse
cameronrwolfe.substack.com
https://epoch.ai/publications/how-much-does-it-cost-to-train-frontier-ai-models
epoch.ai
https://substackcdn.com/image/fetch/$s_!WgYk!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fb3e2bcff-0b6a-4f77-9f18-c3a6a68d4af3_1540x360.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!5por!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ff4cb441a-d31b-4411-83df-219e9d4371a9_1812x658.png
substackcdn.com
Group Relative Policy Optimization (GRPO) Read at the source ↗
cameronrwolfe.substack.com
PPO for LLMs: A Guide for Normal People Read at the source ↗
cameronrwolfe.substack.com
REINFORCE: Easy Online RL for LLMs Read at the source ↗
cameronrwolfe.substack.com
https://cameronrwolfe.substack.com/i/177823868/deepseekmath-pushing-the-limits-of-mathematical-reasoning-in-open-language-models-1
cameronrwolfe.substack.com
https://cameronrwolfe.substack.com/i/153722335/deepseek-r1-zero
cameronrwolfe.substack.com
https://substackcdn.com/image/fetch/$s_!dzfC!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F7d12056e-a139-4bd9-bb4b-00fee858ad9c_2718x1308.png
substackcdn.com
https://cameronrwolfe.substack.com/i/175107358/proximal-policy-optimization-algorithms-1
cameronrwolfe.substack.com
https://cameronrwolfe.substack.com/i/175107358/generalized-advantage-estimation-gae-3
cameronrwolfe.substack.com
https://cameronrwolfe.substack.com/i/175107358/policy-gradient-basics
cameronrwolfe.substack.com
https://cameronrwolfe.substack.com/i/177823868/group-relative-policy-optimization-grpo
cameronrwolfe.substack.com
https://substackcdn.com/image/fetch/$s_!nguf!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F97afd2cb-5a22-4990-a470-4f5bdebb8a53_2124x871.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!CjA3!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F9cd3413a-a68c-4296-89fb-00611fee8016_2314x800.png
substackcdn.com
https://cameronrwolfe.substack.com/i/177823868/implementing-grpo
cameronrwolfe.substack.com
GRPO++: Tricks for Making RL Actually Work Read at the source ↗
cameronrwolfe.substack.com
https://substackcdn.com/image/fetch/$s_!Mm8T!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fff1d7dba-6ade-45c8-bf32-fe2d28992c26_2426x764.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!5Td5!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F91dd2275-150d-423c-87cf-ef7e102f286f_1198x732.png
substackcdn.com
https://cameronrwolfe.substack.com/i/195454629/components-of-an-agent
cameronrwolfe.substack.com
https://yumoxu.notion.site/async-grpo-in-the-wild
yumoxu.notion.site
https://arxiv.org/abs/2504.15930
arxiv.org
https://cameronrwolfe.substack.com/i/198359232/agent-r1-a-unified-and-modular-framework-for-agentic-reinforcement-learning-4
cameronrwolfe.substack.com
https://substackcdn.com/image/fetch/$s_!pUEf!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8b89df74-9ca3-4cfb-bdc9-b64119c9198b_1656x834.png
substackcdn.com
https://drfeifei.substack.com/p/a-functional-taxonomy-of-world-models
drfeifei.substack.com
https://en.wikipedia.org/wiki/Markov_decision_process
en.wikipedia.org
https://substackcdn.com/image/fetch/$s_!g6mE!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffe254f14-9f2c-4e96-bf19-4ed0258648e0_1838x1084.png
substackcdn.com
https://arxiv.org/abs/1911.08265
arxiv.org
https://arxiv.org/abs/2509.24527
arxiv.org
https://gemini.google/overview/image-generation/
gemini.google
https://arxiv.org/abs/2604.14148
arxiv.org
https://profiles.stanford.edu/fei-fei-li
profiles.stanford.edu
https://substackcdn.com/image/fetch/$s_!7-Oh!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F24574361-49e9-4906-8e1c-92306d52d9da_1496x662.png
substackcdn.com
https://arxiv.org/abs/2605.24517
arxiv.org
https://substackcdn.com/image/fetch/$s_!cQLY!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4a68ce47-979c-4fba-8260-798a5bbf326a_2016x1372.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!ESwK!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe068b108-0689-4acc-be03-d0891158927f_1676x1076.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!ScI0!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F1e80ad1e-4d7d-475f-b585-5e7d2b701534_2528x492.png
substackcdn.com
https://arxiv.org/abs/2601.16443
arxiv.org
https://arxiv.org/abs/2606.24855
arxiv.org
https://cameronrwolfe.substack.com/i/195454629/terminal-bench-12
cameronrwolfe.substack.com
https://www.harborframework.com/
harborframework.com
https://cameronrwolfe.substack.com/i/198359232/key-components-of-an-agent
cameronrwolfe.substack.com
https://huggingface.co/Qwen/Qwen3-8B
huggingface.co
https://huggingface.co/Qwen/Qwen3-14B
huggingface.co
https://huggingface.co/open-thoughts/OpenThinker-Agent-v1-SFT
huggingface.co
https://substackcdn.com/image/fetch/$s_!BtKz!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fb0d51c2a-fe62-4012-9fe7-0f97859e1774_1974x728.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!6RhC!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8af17d54-fae6-4fe9-9177-a453afa45a7a_1970x1008.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!m7jq!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa1bfbd7f-da00-4235-8fac-bb7543a07ab9_850x810.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!xQ1q!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fcbea7ed3-8469-4072-be81-1742d66a8286_1822x986.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!vzhb!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa57ddf7e-df82-4553-9cb1-bfe4b7487363_1822x1090.png
substackcdn.com
https://www.primeintellect.ai/blog/true-agents-model-the-world
primeintellect.ai
https://substackcdn.com/image/fetch/$s_!lsvk!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fb532729f-d3cd-4759-9520-744001a8bc5f_2600x1440.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!ybeX!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F7b828532-5ca7-4163-9333-c46b463fad3f_1688x734.png
substackcdn.com
https://en.wikipedia.org/wiki/Forth_(programming_language
en.wikipedia.org
https://substackcdn.com/image/fetch/$s_!nQcO!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd19b0cbb-a636-49b2-83e7-db0cd541079e_2314x882.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!lwq7!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F23c785a1-ecdb-4836-afeb-8c014aea6e6b_2200x856.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!hDAb!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8890d3b4-61ae-4032-bdd8-a15fbb6b96d9_2152x1020.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!1w7p!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fabe536ba-4fc3-4684-8c06-b2bafe709082_1845x974.png
substackcdn.com
https://arxiv.org/abs/2606.02388
arxiv.org
https://substackcdn.com/image/fetch/$s_!00sZ!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0fe83f27-1ef7-4e8e-af57-5d8b259ee0b2_2200x866.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!kqsC!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F78de50da-c6a8-4803-a8a1-e453df23a801_1778x304.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!IwjX!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F53837623-862d-44cf-86e6-8faa22708541_1652x606.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!6GyW!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F64238940-dacb-4201-8f34-160804b2575d_1290x1028.png
substackcdn.com
https://en.wikipedia.org/wiki/Mean_absolute_error
en.wikipedia.org
https://substackcdn.com/image/fetch/$s_!78FL!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd3528571-d302-4501-9744-d871c1876131_2140x736.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!dx4p!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4bdabd96-e27b-477a-98cf-f1e063e7a365_1032x526.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!q1BQ!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F70280740-69a7-4722-a03b-622a6394a39f_1222x702.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!ze7B!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4b4c6c82-d48d-467a-ada4-0fdfd9eade15_1334x298.png
substackcdn.com
https://arxiv.org/abs/2010.03768
arxiv.org
https://arxiv.org/abs/2207.01206
arxiv.org
https://arxiv.org/abs/1809.09600
arxiv.org
https://arxiv.org/abs/1705.03551
arxiv.org
https://arxiv.org/abs/2505.10978
arxiv.org
https://substackcdn.com/image/fetch/$s_!Ip0K!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd9e1da7f-244d-4452-9d23-1fb0e669770b_1706x608.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!FEkQ!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F16befa1a-dc00-4088-94d9-1d31eafd2f9c_1312x538.png
substackcdn.com
https://arxiv.org/abs/2606.24597
arxiv.org
https://substackcdn.com/image/fetch/$s_!fxrE!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Faab4c723-1b8b-42de-981e-6dd50d1c48ff_1628x1124.png
substackcdn.com
https://huggingface.co/collections/Qwen/qwen35
huggingface.co
https://substackcdn.com/image/fetch/$s_!1u0x!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fdade2a02-46ba-4bd9-9b7a-b208a0b8bca8_1402x1426.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!N0lq!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffd52d76a-8bea-439b-a4b3-cfea83fdf7c2_1956x540.png
substackcdn.com
https://cameronrwolfe.substack.com/p/language-model-training-and-inference
cameronrwolfe.substack.com
https://substackcdn.com/image/fetch/$s_!o4Us!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F974682ea-54a8-4a40-a1b8-5c02a352b0b9_1816x916.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!1qyZ!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4b655390-a3c7-4ae6-a727-ada528d2a1fb_1626x462.png
substackcdn.com
Rubric-Based Rewards for RL Read at the source ↗
cameronrwolfe.substack.com
https://substackcdn.com/image/fetch/$s_!DXgh!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F592d3824-8e4c-4220-af6f-4d0ac5f20d8f_1734x1248.png
substackcdn.com
https://cameronrwolfe.substack.com/i/141159804/biases-and-how-we-can-avoid-them
cameronrwolfe.substack.com
https://cameronrwolfe.substack.com/i/181791956/more-tweaks-gspo-gmpo-cispo-and-beyond
cameronrwolfe.substack.com
https://cameronrwolfe.substack.com/i/198359232/ragen-understanding-self-evolution-in-llm-agents-via-multi-turn-reinforcement-learning-7
cameronrwolfe.substack.com
https://substackcdn.com/image/fetch/$s_!tPvT!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F083a3682-3acf-4d24-a798-3607835bde2d_5124x2682.png
substackcdn.com
https://huggingface.co/datasets/Qwen/AgentWorldBench
huggingface.co
https://arxiv.org/abs/2510.25726
arxiv.org
https://substackcdn.com/image/fetch/$s_!jJ3X!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F7a444ff2-c66e-4260-a4b7-4f17dd94e509_6928x2400.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!ZDtb!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F3b03c9e6-637f-48ff-b942-7cac88f89ea9_804x976.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!pSjt!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Ffa44cf69-89f6-4f67-bd76-1b3c81aab1b8_3462x1056.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!z0zo!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fd7096f9a-aac6-4a20-813b-cc446d6bccce_1510x306.png
substackcdn.com
https://cameronrwolfe.medium.com/
cameronrwolfe.medium.com
https://arxiv.org/abs/2506.06266
arxiv.org