---
library_name: transformers
pipeline_tag: text-generation
base_model: Qwen/Qwen3.5-4B
tags:
  - coding-agents
  - context-compression
  - observation-compression
---

# CoACT: Action-Preserving Observation Compression for Coding Agents

This repository contains the pretrained observation compressor released with
[CoACT](https://github.com/THU-Agent/CoACT). The model is a merged Qwen3.5-4B checkpoint
trained from trajectories collected with Qwen3.5-35B-A3B.

CoACT compresses each new environment observation before it enters a coding agent's
trajectory. It is trained with reward-selected supervision that favors compact observations
while preserving the agent's next action.

## Cross-Agent Generalization

Our cross-agent generalization experiments show that compressors trained from different
agentic models achieve similar performance when transferred across agents. When evaluated
with Deepseek-v4-Pro, the compressor trained from Qwen3.5-35B-A3B trajectories achieves
74.5% pass@1 with 0.863M total tokens per instance, close to 75.0% pass@1 and 0.868M total
tokens for the compressor trained from Deepseek-v4-Pro trajectories. These results suggest
that this checkpoint can be used across agentic models without separately training a
compressor for each one, while agent-specific training may still provide a small performance
advantage. We therefore release it as the default CoACT compressor for use across agentic
models.

## Download

```bash
hf download Kndy666/CoACT --local-dir checkpoints/CoACT
```

For deployment and evaluation instructions, see the
[CoACT repository](https://github.com/THU-Agent/CoACT).

For paper, see the [Paper](https://arxiv.org/abs/2607.02911).