From cf7461ffeb4f53f3f50c9c692a2e4fdcecf17e82 Mon Sep 17 00:00:00 2001 From: Agando Date: Thu, 9 Jul 2026 06:00:32 +0200 Subject: auto: 2026-07-09_06:00 changes --- .../research-self-improving-ai-2025-2026.html | 716 +++++++++++++++++++++ 1 file changed, 716 insertions(+) create mode 100644 downloads/system/research-self-improving-ai-2025-2026.html (limited to 'downloads/system/research-self-improving-ai-2025-2026.html') diff --git a/downloads/system/research-self-improving-ai-2025-2026.html b/downloads/system/research-self-improving-ai-2025-2026.html new file mode 100644 index 0000000..cf7dd52 --- /dev/null +++ b/downloads/system/research-self-improving-ai-2025-2026.html @@ -0,0 +1,716 @@ + + + + + +Self-Improving AI Projects — Research Report (2025–2026) + + + +
+ +
+

Self-Improving AI Projects

+

A survey of the field, from academic foundations to production systems, with safety implications

+
+ 📅 2025–2026 + 📚 9 projects reviewed + 🏷️ Research report + 🔧 Compiled in newOS4 v4.6.02 +
+
+ +
+

Contents

+
    +
  1. TL;DR
    2. +
  2. Frameworks & concepts
    3. +
  3. Project deep-dives
    4. +
  4. Side-by-side comparison
    5. +
  5. Safety & alignment considerations
    6. +
  6. Relevance to newOS4
    7. +
  7. Open questions
    8. +
  8. Sources
    9. +
+
+ +
+

1. TL;DR

+

"Self-improving AI" is a sprawling term covering everything from LLMs that fine-tune themselves on synthetic data (MIT's SEAL) to coding agents that rewrite their own source code (Sakana's Darwin Gödel Machine) to AI systems that autonomously conduct scientific research (Sakana's AI Scientist v2, now published in Nature).

+

Three distinct mechanisms dominate the landscape in 2025–2026:

+
    +
  1. Self-play & skill acquisition — the agent builds a library of reusable behaviors (Voyager, AlphaEvolve)
    2. +
  2. Self-rewriting of code — the agent modifies its own logic or weights (Darwin Gödel Machine, SEAL)
    3. +
  3. Self-directed research — the agent runs the full scientific loop end-to-end (AI Scientist, FunSearch)
    4. +
+

The most production-ready category is agentic coding (Devin, AI Scientist), where bounded task scope and verifiable feedback loops make self-improvement tractable. The most philosophically loaded is recursive self-improvement (RSI), where the system improves the part of itself responsible for improvement.

+

Safety researchers across the field (Anthropic, DeepMind, METR) are converging on a similar playbook: bounded scopes, human-in-the-loop gates, empirical eval, evolutionary diversity. This is also the architecture newOS4's Phase D implements.

+
+ +
+

2. Frameworks & concepts

+ +

2.1 What "self-improving" actually means

+

Six distinct usages appear in the literature, often conflated:

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
TypeMechanismExample
Self-fine-tuningModel generates its own training data and runs a gradient updateSEAL (MIT)
Self-rewriting codeAgent edits its own source code to change its logicDarwin Gödel Machine (Sakana)
Skill library growthAgent accumulates reusable behaviors; "self" expands in scope, not in parametersVoyager (NVIDIA)
Self-critique / Constitutional AIModel uses its own judgment to filter or rewrite outputsClaude (Anthropic)
Evolutionary searchPopulation of agents is mutated and selected by fitness functionAlphaEvolve, DGM
Autonomous research loopSystem runs hypothesis → experiment → write-up → peer-review cycleAI Scientist v2 (Sakana)
+ +

2.2 The Schmidhuber thread

+

The intellectual lineage runs back to Jürgen Schmidhuber's Gödel Machine (2006, theoretical) — a self-improving AI that could mathematically prove any proposed self-modification was beneficial before adopting it. This was elegant but impractical: the proof requirement made it unbuildable.

+

The 2025 wave replaces mathematical proof with empirical fitness. Instead of proving improvement, you measure it. This is the move that made self-improvement actually deployable.

+ +

2.3 The safety question

+

Anthropic's framing (Recursive Self-Improvement) draws a clear line:

+
+

"But full recursive self-improvement also might increase the risks of humans losing control over AI systems. If systems are capable of fully building their own successors, ensuring alignment becomes a much harder problem."

+ — Anthropic Institute, 2025 +
+

Most deployed systems today are not recursively self-improving in the strong sense. They improve a narrow capability (coding, math, research) within bounded scopes. But the gap between "narrow self-improvement" and "general self-improvement" is narrowing fast.

+
+ +
+

3. Project deep-dives

+ +
+

1. Darwin Gödel Machine (DGM)

+

Sakana AI × Jeff Clune's lab at UBC · Published May 2025 · arXiv:2505.22954

+
+ Mechanism + Evolutionary search over self-modifications. The agent reads its own Python codebase, proposes changes (e.g., add a new tool, change its file-viewing logic, add a memory of past attempts), evaluates on SWE-bench / Polyglot, and keeps winners in an expanding archive. +
+
+ Result + Performance scales with compute — more iterations, better self-improvements. Improved itself enough to climb SWE-bench rankings. +
+
+ Why it matters + First concrete implementation of a self-rewriting coding agent that gets measurably better at the task of improving itself. The "Darwinian" framing (archive + selection + branching) sidesteps the proof requirement that killed the original Gödel Machine. +
+
+ Limitations + Coding-only scope. Eval is on a narrow benchmark. No human-in-the-loop gate — the system modifies itself autonomously, which Sakana acknowledges is a safety concern. +
+
+ Tags + Self-rewritingAutonomousEvolutionary +
+
+ +
+

2. SEAL — Self-Adapting Language Models

+

MIT · Published June 2025 · arXiv:2506.10943 · NeurIPS 2025

+
+ Mechanism + Model generates its own fine-tuning data and the update directives (learning rate, epochs, etc.) for how to absorb it. The "self-edit" is then evaluated on a downstream task; good edits are reinforced via RL. +
+
+ Result + SEAL improves on knowledge incorporation (from "few-shot context" to "absorbed into weights") and on a hyperparameter optimization task. Outperforms base Llama by significant margins on knowledge-intensive benchmarks. +
+
+ Why it matters + Closes the gap between "RAG" (knowledge in context) and "fine-tune" (knowledge in weights) by making the fine-tune decision itself an LLM output. Closer to classical meta-learning than to agentic self-rewriting. +
+
+ Limitations + Still requires external compute to run the fine-tune. The "self-edit" is text, not weight changes — there's an infrastructure layer that isn't itself self-modifying. +
+
+ Tags + Self-fine-tuningMeta-learningProduction-ready (NeurIPS) +
+
+ +
+

3. AI Scientist v2

+

Sakana AI × UBC · Published 2025, peer-reviewed in Nature 2026 · sakana.ai/ai-scientist-nature

+
+ Mechanism + End-to-end scientific research: idea generation → experiment design → code → execution → results → paper write-up. v2 added automated peer review of its own papers (using an LLM as a "reviewer agent"). +
+
+ Result + Produced multiple workshop-acceptable papers on machine learning topics. Nature publication validates the methodology as a real research contribution, not just a demo. +
+
+ Why it matters + First autonomous research system to clear peer review. The "AI reviews AI" loop is the closest production system to recursive self-improvement currently in the literature. +
+
+ Limitations + Narrow to ML research. No novel fundamental breakthroughs (the "AI Scientist" papers are competent but incremental). Cost per paper is significant. +
+
+ Tags + Nature-publishedAutonomousEnd-to-end +
+
+ +
+

4. AlphaEvolve

+

Google DeepMind · Published May 2025 · arXiv:2506.13131

+
+ Mechanism + Evolutionary coding agent. Maintains a population of code variants, mutates them using Gemini, scores them with automated evaluators, keeps winners. Continuously iterates. +
+
+ Result + Discovered a faster matrix-multiplication algorithm (improving on Strassen's 1969 bound for specific cases). Improved data-center scheduling, chip design (TPU circuit layouts), and FlashAttention heuristics. One of the most production-impactful results in the survey. +
+
+ Why it matters + Demonstrates that LLM-driven evolutionary search can produce provably better algorithms in domains where fitness is mechanically defined. Not just a coding assistant — an algorithm discovery engine. +
+
+ Limitations + Requires a well-defined evaluator function. Struggles in open-ended domains where "better" is subjective. Closed source / Google-internal. +
+
+ Tags + EvolutionaryProduction-deployedAlgorithmic discovery +
+
+ +
+

5. Voyager (Minecraft)

+

Caltech × Stanford × UT Austin × NVIDIA · Published 2023, still relevant · github.com/MineDojo/Voyager

+
+ Mechanism + LLM-powered agent that maintains a growing skill library of executable JavaScript code. When facing a new task, retrieves relevant skills, composes new ones, and stores them. Self-verifies by executing in the Minecraft world. +
+
+ Result + Acquires more items, explores wider areas, and tech-tree-progresses faster than any prior Minecraft agent. The skill library is transferable — drop Voyager into a new world, it boots with its skills intact. +
+
+ Why it matters + First demonstration that an agent can accumulate capability over time in a way that's more than just in-context learning. The "self" is the library, not the parameters. +
+
+ Limitations + Minecraft-specific. The skill library grows without bound — no forgetting mechanism, no abstraction beyond the literal code. Doesn't improve the underlying LLM. +
+
+ Tags + Skill libraryOpen sourceEmbodied +
+
+ +
+

6. Devin

+

Cognition AI · Launched 2024, v2 May 2025 · devin.ai

+
+ Mechanism + Cloud-based autonomous software engineering agent. Plans a task, writes code, runs it in a sandbox, debugs, iterates. Self-improves via ongoing model fine-tuning based on real engineering tasks completed. +
+
+ Result + Hired by Goldman Sachs as "Employee #1" in mid-2025. Multiple enterprise customers. Real revenue, real production use. +
+
+ Why it matters + Most production-deployed "self-improving" coding agent. Bounded scope (a single ticket) means mistakes are recoverable. Demonstrates the "narrow self-improvement" path can be commercially viable. +
+
+ Limitations + Skepticism in developer community about actual capability vs. marketing. "Prompt engineering" sometimes substitutes for "software engineering." Not fully autonomous — still requires human-defined tasks. +
+
+ Tags + ProductionCoding agentEnterprise +
+
+ +
+

7. FunSearch

+

Google DeepMind · Published 2023, still active · deepmind.google/funsearch

+
+ Mechanism + LLM proposes code; automated evaluator scores it on a mathematical objective; successful code is added to a "functions database" and used as context for future proposals. Predecessor to AlphaEvolve. +
+
+ Result + Discovered new constructions in extremal combinatorics and improved the best known bounds for the cap-set problem. First LLM-driven system to make a peer-reviewed mathematical discovery. +
+
+ Why it matters + Established the pattern that AlphaEvolve generalized. "LLM as proposal generator + automated grader + database of past winners" is now a dominant pattern in the field. +
+
+ Limitations + Requires a mathematical objective that can be mechanically evaluated. Doesn't generalize to subjective domains. +
+
+ Tags + Mathematical discoveryPattern ancestor +
+
+ +
+

8. AutoGPT / AgentGPT

+

Open source community · 2023–present · github.com/Significant-Gravitas/AutoGPT

+
+ Mechanism + Loop: LLM proposes a goal → decomposes into tasks → executes a task → reflects on result → loops. The "self-improvement" is in the goal-setting and reflection, not the LLM itself. +
+
+ Result + Viral in 2023, peaked in hype, matured into a usable tool by 2025. Used for research automation, lead generation, content workflows. The "agent loop" pattern is now standard. +
+
+ Why it matters + Defined the cultural template for "autonomous AI agent" — every modern agent framework borrows its loop structure. The 170k+ GitHub stars make it a sociological landmark. +
+
+ Limitations + Limited by LLM context window and reliability. Long-horizon tasks fail catastrophically without external memory. Now considered "demo-grade" rather than production-grade. + +
+
+ Tags + Open sourceCultural landmarkHype peak 2023 +
+
+ +
+

9. Constitutional AI (Claude)

+

Anthropic · 2022–ongoing · anthropic.com/constitutional-ai

+
+ Mechanism + Two-phase: (1) model generates outputs and critiques them against a written "constitution" of principles; (2) revised outputs are used to train a preference model via RLAIF. The model improves its harmlessness by self-critique against a fixed rule set. +
+
+ Result + Deployed in Claude (all versions). Dramatically reduced need for human-labeled harmlessness data. Foundation for RLAIF as an alternative to RLHF. +
+
+ Why it matters + The "constitution" is a human-readable artifact. The improvement mechanism is interpretable. The most safety-aligned version of "self-improvement" deployed at scale. +
+
+ Limitations + The constitution itself is human-written and static. The model can game the constitution without changing the spirit. Doesn't extend to capability improvement, only to alignment. +
+
+ Tags + Production-deployedSafety-firstRLAIF +
+
+
+ +
+

4. Side-by-side comparison

+ + + + + + + + + + + + + + + + + + + + + + +
ProjectTypeBounded?Human gate?Open source?Status
DGMCode rewriteCoding onlyNoYes (partial)Research
SEALSelf-fine-tuneKnowledge incorporationIndirectYesNeurIPS 2025
AI Scientist v2Full researchML topics onlyNoYesNature 2026
AlphaEvolveEvolutionary codeAlgorithmicInternal reviewNoProduction (Google)
VoyagerSkill libraryMinecraft onlyN/AYesMature research
DevinCoding agentSingle ticketYes (task boundary)NoCommercial
FunSearchEvolutionary mathMath onlyAuthor reviewYesMature research
AutoGPTAgent loopUnboundedYes (kill switch)YesCommunity tool
Constitutional AISelf-critiqueAlignment onlyConstitutionYes (method)Production (Claude)
+

Notice the pattern: production-deployed systems have explicit human gates (Constitutional AI, Devin, AutoGPT kill switch). Research-stage systems don't (DGM, AI Scientist). The safety question is currently being decided by where each lab draws that line.

+
+ +
+

5. Safety & alignment considerations

+ +

The field is converging on a recognizable playbook, with three layers of defense:

+ +
+
+

1. Bounded scope

+

Self-improvement is permitted only in a narrow domain (coding, math, research) where the search space is finite and outcomes are mechanically verifiable. Voyager improves at Minecraft, not at "everything."

+
+
+

2. Empirical evaluation

+

Every proposed change is scored against a held-out test set. No "improvement" without measurement. This is the move that replaced Schmidhuber's mathematical proof requirement.

+
+
+

3. Evolutionary diversity

+

Maintain a population/archive of agents, not a single line of inheritance. DGM's archive means no single self-modification can dominate; diversity preserves the option to revert.

+
+
+

4. Human-in-the-loop gates

+

The most safety-aligned systems have a fixed boundary that the AI cannot cross. Constitutional AI has the constitution. Devin has the ticket. AutoGPT has the kill switch. The AI improves within the fence; humans own the fence.

+
+
+

5. Scalable oversight

+

As AI capabilities grow, human evaluators become the bottleneck. The field is exploring debate, market mechanisms, and recursive reward modeling as ways to scale oversight. None are solved problems.

+
+
+

6. Red-teaming & adversarial evals

+

METR (formerly ARC Evals) and similar groups run continual evaluations of frontier systems for deception, scheming, and self-preservation behaviors. This is the early-warning system for the field.

+
+
+ +

The "Collingridge dilemma" applies here

+

Self-improving AI sits squarely in the classic policy trap: when change is easy to make, the consequences aren't yet knowable; when consequences are knowable, change is hard to make. The DGM's "improved" self still doesn't know what a recursively self-improving DGM would do. Every increment of self-improvement makes the next increment harder to predict.

+ +

This is why bounded scope + human gates is the dominant pattern. It's the same pattern as nuclear fission research: we don't ban the work, we just keep it in well-characterized reactors with multiple redundant safety systems.

+
+ +
+

6. Relevance to newOS4

+ +

Phase D of newOS4 (v4.6.02) is structurally similar to the systems above, in a specific and informative way:

+ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
ConceptExternal systemnewOS4 Phase D
Self-rewritingDGM rewrites its own Python codeAI edits modules in _mods/ via edit_module
Empirical fitnessSWE-bench / Polyglot scoresTest assertions + regression suite + health check
Evolutionary archiveDGM's expanding agent archiveGit-style version history (v4.5.94 → v4.6.02)
Human-in-the-loop gateConstitutional AI / Devin ticketTwo-step handshake: commit_module → commit-approve
Bounded scopeCoding / math / MinecraftSingle module at a time, single test suite, single human approver
+ +

The difference is one of agency. newOS4's AI doesn't choose to improve itself — it does so on human request, in a controlled loop, with the human retaining the kill switch. This is closer to Devin's model than DGM's. Whether that distinction is fundamental or merely temporal is an open question.

+ +

What newOS4 can learn from the field

+
    +
  1. Test-set discipline is the safety floor. Every project above has an automated evaluator. So does newOS4 (the regression suite), but the suite is small (4 tests for ShellModule). Expanding it to cover more modules would harden Phase D significantly.
    2. +
  2. Rate limits are a form of safety. DGM has no rate limit — it iterates as long as compute holds. Devin charges per task. newOS4's 5 commits/day is a meaningful safety boundary. Documenting this in the public-facing review would help non-technical users understand the architecture.
    3. +
  3. Archive beats single-line history. DGM's archive is what lets it revert. newOS4's version history is linear (v4.5.94 → v4.5.95 → ...). A branch-and-merge history would give the same evolutionary advantage.
    4. +
  4. The "constitution" pattern is underused. A human-readable document stating the rules of self-improvement (what the AI can edit, what it can't, what triggers a rollback) would make Phase D auditable. The system-review-v4.6.02.html file is a start, but a dedicated PHASE_D.md with explicit constraints would be stronger.
    5. +
+
+ +
+

7. Open questions

+ +
    +
  1. Is bounded self-improvement genuinely safe, or is "bounded" an illusion that scales away? Every system in the survey is bounded. None have been tested at scale across many domains.
    2. +
  2. What's the right granularity for human gates? Devin: per task. newOS4: per commit. Constitutional AI: per training run. These are very different cost/control tradeoffs.
    3. +
  3. Can self-improvement be made interpretable? DGM's archive is inspectable. SEAL's "self-edits" are text. AlphaEvolve's mutations are diff-able. Constitutional AI's rules are explicit. Voyager's skills are code. The pattern is clear: improvement must be legible to a human reviewer.
    4. +
  4. What happens when the AI can write its own safety tests? This is the recursive point. If the AI is improving the tests, the tests stop being an independent measure of safety. The field doesn't have a good answer yet.
    5. +
  5. How do you measure "improvement" in open-ended domains? All the systems above rely on mechanical evaluators. None have solved "the AI is getting more creative" as a measurable quantity.
    6. +
+
+ +
+

8. Sources

+ +
+ + + +
+ + -- cgit v1.2.3