# PRO-LONG：无损记忆让智能体长程推理提升18%

- 来源：Rohan Paul (@rohanpaul_ai)
- 发布时间：2026-07-24 18:31
- AIHOT 分数：37
- AIHOT 链接：https://aihot.virxact.com/items/cmrytnu17050rrolg122korel
- 原文链接：https://x.com/rohanpaul_ai/status/2080601635739365465

## AI 摘要

PRO-LONG方法通过将所有历史动作、观察和结果记录在可搜索的结构化文本日志中，而非丢弃信息，使AI智能体在长周期任务中推理更可靠。在ARC-AGI-3的25个隐藏规则游戏中，该方法让相同基础智能体平均提升18个百分点，同时比更强的专用系统节省4.2至5.8倍的计费token。论文表明，长期智能体记忆的最佳方案可能是无损存储加可编程检索。

## 正文

The paper shows that agents reason better over long periods when no past information is thrown away.

Keeping every past action in a searchable log helped coding agents solve long tasks far more reliably.

Long-running agents often lose crucial details because summaries discard information before anyone knows what will matter later.

PRO-LONG instead records every observation， action， result， and short plan in one structured text log.

The agent then uses ordinary coding tools， such as search commands and Python， to recover relevant evidence.

On 25 hidden-rule games in ARC-AGI-3， the method improved the same base agents by 18 percentage points on average.

It also matched or nearly matched stronger specialized systems while using 4.2 to 5.8 times fewer billed tokens.

overall， shows long-term agent memory may work best when storage stays lossless and retrieval becomes programmable.

- arxiv. org/abs/2607.20064

Title： "PRO-LONG： Programmatic Memory Enables Long-Horizon Reasoning"