Self-Improving Loops

Three papers landed in November 2026, from Google, from Google Cloud and DeepMind with Penn State, and from Meta. They work on different problems: an agent harness that rewrites itself, a memory that lets improvement survive a change of model, and a factory that manufactures benchmarks. Underneath, all three are the same machine. This site explains that machine completely: what it is, what the evidence actually shows, where it breaks, and what to build with it.

The skeleton, in plain language

A loop edits an artifact. The artifact is code or configuration around a model: a harness, a memory file, a benchmark definition. The model's weights never change.

Each round starts from fresh context. The loop does not carry a long, decaying conversation. It re-reads its state from files at the start of every iteration, does one bounded step, and writes the state back.

State lives in files. Past attempts, scores, diagnoses, and predictions sit in structured files that any later round, or a human, can inspect. Nothing important exists only inside a model's memory of the conversation.

A frozen check the loop cannot game decides what survives. Something outside the loop's edit reach renders the verdict: a held-out test set in read-only storage, a set of quality anchors fixed before any run, a grader the loop is forbidden to touch. The proposer can be as creative as it likes. It cannot move the goalposts, because it cannot reach them.

That is the whole idea. Everything on this site is an elaboration: how each paper builds the machine, what breaks when a part is missing, and how to point the same machine at cybersecurity, where the checks happen to be unusually honest.

The three papers, one line each

A fourth paper, TRUST (arXiv:2611.10787), replaces the acceptance gate with a statistical one and measures how often a score-greedy gate accepts changes that are actually worse (45.59% in its experiments, abstract-level). It gets its own shorter page because it answers the question the other three leave open: how do you know the gate itself works?

Site map

Prerequisites (read these first if the vocabulary is new)

The papers

Synthesis and application

Three reading paths

The 30-minute version

  1. This page.
  2. The Loop, for the vocabulary.
  3. The Complete Synthesis, for the architecture, the comparison table, and the evidence-strength table.
  4. The "in one breath" summary at the top of each paper page.

The complete version

  1. All four prerequisite pages, in order: The Loop, Verifiers and Graders, Benchmarks, Two Spaces.
  2. The three paper pages in order, then TRUST.
  3. The Complete Synthesis.
  4. The Cyber Version.
  5. The Reading Path, for everything underneath.

The builder's version

  1. Verifiers and Graders and Benchmarks, because every build stands or falls on its check.
  2. Paper 3: Benchmark Factory, because most of the seven builds are its direct descendants.
  3. The "adversarial read" section of the synthesis, because it lists the weaknesses a build inherits.
  4. The Cyber Version, practice section.
  5. The Build Book, in dependency order.

A note on evidence

Numbers on this site carry their conditions: sample sizes, which model, which split, how many runs, who ran the experiment. Claims are marked by kind, using six labels:

Reading coverage, stated precisely: Paper 1 and Paper 3 were read in full text. Paper 2 was read in its main text, Tables 1 to 3, Limitations, Ethics, and Appendix F in full; its Appendices B to E were skimmed, not read line by line, and the Paper 2 page flags that. TRUST was checked at abstract level only. The prerequisite entries were checked against their arXiv records.

An adversarial review panel was also run: one model (in Perplexity), in two threads, from one origin. The site uses its valid criticisms and names its errors, including a confident and false claim that Paper 1 reports no first-party numbers. Where a paper's own numbers undercut its headline, the site says so. That habit is, not coincidentally, the subject of the site.