corpus.blog
56,966 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a08724-e7fd-72f9-a94d-b370e2e7bfba

Language model harnesses are compositional generalizers

alexzhang13.github.io · 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 alexzhang13.github.io Wayback capture
3blogs citing
First cited
16 Jul 2026
Most recent
26 Aug 2026
Rank this month
not ranked
Links from this post
22
Words captured
5,329

Cited by

Blog
In the post
Date
clef-lang.com
Beyond the Bitter Lesson: Structural Convergence Read at the source ↗
26 Aug 2026
iurysouza.dev
Principles for Solving long horizon tasks with Harness Engineering Read at the source ↗
27 Jul 2026
Dan MacKinlay
Agent harness design Read at the source ↗
16 Jul 2026

Links from this post

Link
Host
https://arxiv.org/abs/1706.03762
arxiv.org
Recursive Language Models Read at the source ↗
alexzhang13.github.io
The Mismanaged Geniuses Hypothesis Read at the source ↗
alexzhang13.github.io
https://www.trychroma.com/research/context-rot
trychroma.com
https://www.anthropic.com/engineering/managed-agents
anthropic.com
https://arxiv.org/abs/2505.09388
arxiv.org
https://arxiv.org/abs/2507.20534
arxiv.org
https://arxiv.org/abs/2602.15763
arxiv.org
https://arxiv.org/abs/2210.03629
arxiv.org
https://arxiv.org/abs/2402.01030
arxiv.org
https://code.claude.com/docs/en/overview
code.claude.com
https://openai.com/codex/
openai.com
https://verl.readthedocs.io/en/latest/algo/rollout_corr_math.html
verl.readthedocs.io
https://github.com/google-deepmind/eval_hub/tree/master/eval_hub/mrcr_v2
github.com
https://huggingface.co/datasets/openai/graphwalks
huggingface.co
https://arxiv.org/abs/2601.02872
arxiv.org
https://arxiv.org/abs/2511.02817
arxiv.org
https://www.alphaxiv.org/abs/2512.24601
alphaxiv.org
https://arxiv.org/abs/2404.06480
arxiv.org
https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507
huggingface.co
https://github.com/alexzhang13/rlm/blob/main/rlm/utils/prompts.py
github.com
https://noahziems.com/pedagogical-rl
noahziems.com