SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2606.26758 · ICML · 2026

EGG: An Expert-Guided Agent Framework for Kernel Generation

Ke Fan, Yaochen Han, Hongxu Jiang, Wanqi Xu, Weiyu Xie, Runhua Zhang, Chenhui Zhu, Yixiang Zhang

arXiv · PDF · Open in the Atlas

Code that ran

None of the 3 samples (functions and classes) lifted from this paper's linked repositories has a recorded run on a synthesized input (3 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2606.26758.json · badge: /api/ran/2606.26758.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
turbo-llm/turbo-alignment canonical (classifier label)
classifier basis: census
0 ran · 3 no recorded run
FunctionStatusWhere it lives
get_tensor_model_parallel_group Not yet run
unverified (harvested, no recorded run)
turbo-llm/turbo-alignment/turbo_alignment/modeling/parallel_states.py
code served (permissive licence) · get_code("b79308e167d3dee8")
How it ran

no invocation recorded.

is_pipeline_first_stage Not yet run
unverified (harvested, no recorded run)
turbo-llm/turbo-alignment/turbo_alignment/modeling/parallel_states.py
code served (permissive licence) · get_code("22d5b586bf7f0c83")
How it ran

no invocation recorded.

is_pipeline_last_stage Not yet run
unverified (harvested, no recorded run)
turbo-llm/turbo-alignment/turbo_alignment/modeling/parallel_states.py
code served (permissive licence) · get_code("f16d8d2d474eba7a")
How it ran

no invocation recorded.

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 2 are also present in other papers whose code we hold (2 with at least one paper dated earlier, 0 the same month, 0 later) and 1 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
is_pipeline_first_stage 1 other paper
1 dated earlier
2404.03608 (2024-04)
Sailor: Open Language Models for South-East Asia
is_pipeline_last_stage 1 other paper
1 dated earlier
2404.03608 (2024-04)
Sailor: Open Language Models for South-East Asia

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

High-performance GPU kernels are critical for reducing the exponentially growing computational costs of large language models (LLMs), but their development heavily relies on manual tuning by domain experts. While recent advances in LLMbased approaches show promise for automating kernel generation, they still struggle to achieve both correctness and high performance. This limitation primarily arises from the lack of domainspecific optimization guidance, hindering effective exploration of the optimization space. We propose EGG, an Expert-Guided Agent Framework for Kernel Generation, which incorporates expert optimization principles to guide LLMs' decisions. Inspired by expert workflows, we decompose kernel generation into two hierarchical stages: 1) algorithmic structure design, which establishes a high-quality computational structure foundation; 2) hardware-specific tuning, which performs targeted adjustments through parallel mapping, tensor tiling, and memory optimization. This staged decomposition defines explicit optimization objectives, structuring the design space to achieve progressive refinement. To this end, a stage-aware multi-agent collaboration mechanism is designed for inter and intra-stage context management, ensuring stable optimization trajectories. Experiments on KernelBench and real-world workloads show that EGG achieves a 2.13× average speedup over PyTorch, outperforming existing agent-based and RL-based approaches.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2606.26758")
get_code_for_paper("2606.26758")
have("2606.26758")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2606.26758.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2606.26758.svg)](https://syntology.ai/paper/2606.26758)

Connect an agent — have() is free.