---
title: "CompressionBench: How can your coding agents compress LLMs?"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.06858v1"
permalink: "https://feed.astralor.com/items/itm_252abaf75018efc5a3a6ebb2"
published: "2026-11-04T18:14:50.000Z"
score: 59
channel: "tech"
tags: ["LLM","AI Agent","推理效率","RAG","多模态","CompressionBench","LLMs","Recursive"]
---

# CompressionBench: How can your coding agents compress LLMs?

## At a glance

Recursive self-improvement requires AI systems to improve the models and infrastructure used by subsequent systems. LLM compression offers a concrete efficiency objective: retain a pretrained model's behavior within a s…

## Key points

- Recursive self-improvement requires AI systems to improve the models and infrastructure used by subsequent systems.
- LLM compression offers a concrete efficiency objective: retain a pretrained model's behavior within a smaller model storage budget.
- We study whether coding agents can carry out this step autonomously.

## Full text

Recursive self-improvement requires AI systems to improve the models and infrastructure used by subsequent systems. LLM compression offers a concrete efficiency objective: retain a pretrained model's behavior within a smaller model storage budget. We study whether coding agents can carry out this step autonomously. We formulate compression as a terminal task in which an agent receives a source checkpoint, storage limit, inference environment, and time budget, then constructs compressed weights and executable inference code. The agent controls its algorithm and experiments; perplexity feedback guides search, and independent verification checks the final model. Across six agents and six model--size settings, 29 of 36 submissions pass verification. Selecting the lowest-perplexity agent design per task yields an average 3.4% perplexity increase over BF16 and 77.33% downstream accuracy, compared with 79.56% for BF16. Recorded experiments reveal how agents achieve these outcomes and where improvement breaks down. Agents lower PPL in 21 of 24 revisions at nearly fixed storage; complete-model feedback reverses 17 of 79 prior local rankings; and generation and inference tests expose failures that likelihood alone misses. The results identify representation design, experimental judgment, and capability validation as central to agent-driven model compression, a measurable component of efficiency-oriented self-improvement.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_252abaf75018efc5a3a6ebb2