---
title: "Self-Improvement"
description: "1 posts about Self-Improvement, summarised, each linking to the original."
---

# Self-Improvement
> 1 posts about Self-Improvement, summarised, each linking to the original.

## Articles

### [RLTL;DR: Self-Improvement by Internalizing Self-Generated Feedback](https://yomu.fyi/post/rltl-dr-self-improvement-by-internalizing-self-generated-feedback.md)
- Company: [Apple](https://yomu.fyi/company/apple.md)
- Published: Oct 1, 2026
- Type: Announcement

Standard reinforcement learning with verifiable rewards (RLVR) fails when tasks are so difficult that agents have no chance of success and no teacher models exist. RLTL;DR addresses this by having the policy write its own TL;DR insight after each failed attempt, conditioning the next rollout on all previous insights. Backpropagation on the in-context insights internalizes a direct task-to-insight mapping. On challenging tool-calling and coding datasets filtered to Pass@128=0, standard GRPO training stays flat at 0-1% Pass@1, while RLTL;DR achieves 14-31% Pass@1 with insights in context during training and 12-13% without at eval time. Reducing to SFTL;DR, training on only 4k (task, insight) tuples without rollouts, recovers almost full performance of RLTL;DR and classical SFT, demonstrating a promising compacted training paradigm.