Notes from the Ethereum Basis’s Protocol Safety crew on working coordinated AI brokers towards actual protocol code, together with how we arrange the work, what holds up underneath scrutiny, and what shopper groups and safety researchers can take from it. This submit stands by itself; later posts will go deeper on particular person shoppers.
What we have been working, and what stunned us
On the Ethereum Basis’s Protocol Safety crew, we have been working coordinated AI brokers towards the sorts of methods the community will depend on, like methods software program, cryptographic code, and contracts that should be proper. The brokers discovered actual bugs. One is now public: a remotely-triggerable panic in libp2p’s gossipsub, a core a part of the peer-to-peer layer Ethereum consensus shoppers run on, fastened and disclosed as CVE-2026-34219 with credit score to the crew.
Brokers discovering bugs wasn’t the shock. The shock was how little of the work went into discovering them, and the way a lot went into telling the true bugs from those that simply seemed actual.
This submit is for shopper groups and safety researchers who wish to do the identical factor. It covers how we arrange the brokers, the bar a candidate has to clear earlier than it counts as a discovering, and the habits that hold the outcomes reliable.
Groups elsewhere are converging on the identical recipe. Anthropic’s Frontier Pink Crew constructed an agent that writes property-based exams and located actual bugs throughout the Python ecosystem. Cloudflare ran a frontier mannequin by way of a security-research harness towards their very own methods. Everybody lands on the identical loop: level a succesful mannequin at a codebase, let it search, and triage what comes again. So the true query is how to do that with out drowning in confident-sounding noise.
One caveat up entrance: tooling for agent-driven audits strikes quick, and any particular setup is old-fashioned in just a few weeks. So this submit is intentionally in regards to the strategies, that are persistent, quite than the tooling. Disclosure is its personal matter and can most likely be its personal submit.
An agent pointed at a codebase is a search software, rather a lot like a fuzzer. The distinction is what comes again. A fuzzer arms you a crash and a stack hint. An agent arms you much more, together with a write-up (name chain, impression declare, prompt severity) and the artifacts to again it, like a proof-of-concept you may run towards the true code.
All of that makes the end result simple to learn and simple to belief, the working proof-of-concept most of all. So do not depend what number of candidates an agent produces. Depend what number of grow to be actual.
How the work is organized
We run many brokers in parallel towards one goal. They coordinate by way of the repository itself, with shared state in model management and no central course of handing out work. An agent writes down a declare the place the others can see it, does the work, and commits.
We bought this strategy from Anthropic’s writeup on constructing a C compiler with a fleet of brokers, which coordinates the identical means. There is no central coordinator to construct or preserve, and fewer that may go incorrect.
The roles are generated by the work that is found:
Recon turns an assault floor into concrete, testable hypotheses. Not “audit the decoder” however “this subject is trusted previous this level; this is the property it ought to hold, the way in which it would break, and the proof that will settle it.”Looking takes one speculation, traces the code path, and tries to construct a reproducer.Hole-filling seems to be at what was accepted and what was rejected, writes the subsequent batch of hypotheses, and tracks protection so the brokers do not hold going over the identical floor.Validation re-checks every candidate independently, removes duplicates, and decides.
We did not invent this pipeline. Cloudflare describes the identical phases, recon, parallel looking, unbiased validation, deduplication, reporting, and their writeup helped form ours.
This is what a candidate seems to be like earlier than it counts as a discovering:
invariant: the property that should maintain
mechanism: the precise means it is likely to be made to break
success: observable proof: a panic, a stall, an accepted-invalid enter
reproducer: a self-contained artifact that runs towards the true code
dedup: a key, so two brokers do not chase the identical factor
The schema is there for a motive. It forces a selected, testable declare and a transparent definition of achieved. An agent that has to jot down down an observable proof cannot fall again on “this seems to be dangerous.”
Reproducible or it did not occur
One rule issues greater than another. A candidate is not a discovering till there is a self-contained artifact that reproduces the failure towards the true code, and that runs for somebody who did not write it.
The reproducer does not learn the write-up, and it does not care how assured the mannequin sounded. It both runs or it does not.
Most of its worth is within the false positives it catches. Three of them come up again and again, and every one is the agent getting a cross for the incorrect motive:
A panic that solely occurs in a debug construct. Compile and run it the way in which the software program really ships, and the worth simply wraps round. Nothing crashes. It seems to be like a crash, but it surely is not one.A reproducer that builds some inside worth by hand, one no actual enter may ever produce, as a result of each path an attacker controls rejects it earlier. The bug solely “reproduces” towards a operate that nothing reachable calls that means.In formal-verification work, a proof that goes by way of however doesn’t suggest what you wished. The assertion is trivially true no matter what the code does, or it is weaker than the property you meant to seize. The verifier is glad, however the theorem does not constrain the habits you really cared about.
None of that is new. It is the identical factor as a take a look at that passes as a result of it does not really test something. What’s new is the amount. An agent writes the ineffective model as quick as the true one, and simply as confidently. So the test must be automated. You possibly can’t depend on the agent to catch itself.
Sign-to-noise is a lot of the work
Most candidates are incorrect, duplicate, or out of scope. That is not an issue with the strategy; that is the way it works. The aim is to reject the incorrect ones quick and again the true ones with proof that is arduous to argue with.
Each candidate that survives will get two unbiased checks. Can an actual attacker really attain it in a traditional configuration? And what does it price the attacker to tug off, in comparison with what it prices the community if it really works? A bug that any single peer can set off could be very completely different from one which wants particular entry or an enormous quantity of sources.
Every little thing will get checked towards a working checklist of what is already identified, fastened, or rejected. With out that, the brokers hold rediscovering the identical closed concern and reporting it repeatedly.
Acceptance charges differ rather a lot from goal to focus on, and that variation is helpful by itself. Run this towards mature, closely audited code and virtually nothing survives, which continues to be value figuring out. “We seemed arduous and located nothing” is an actual end result. Run it towards less-explored code, or towards formally verified code, the place a machine-checked proof covers a mannequin and the deployed bytecode is just assumed to match it, and extra will get by way of.
We’re not the one ones who discovered that the triage is the arduous half. Cloudflare’s principal takeaway was {that a} slender scope beats broad scanning. Anthropic’s property-based-testing agent generated one thing like a thousand candidate reviews, then used rating and knowledgeable assessment to get right down to a high tier that held up about 86 % of the time. The technology was the simple half. I am not going to publish our personal numbers right here; tied to a selected goal, they’d say extra in regards to the goal than in regards to the methodology.
What the brokers are good at, and the place they mislead
There’s hype in each instructions, so this is a plain checklist of what the brokers do nicely and the place they mislead.
The cut up is not even regular from one job to the subsequent. Stanislav Fort, testing a variety of fashions on actual vulnerabilities, calls this a jagged frontier, or a mannequin that recovers a full exploit chain on one codebase can fail primary data-flow tracing on one other. You possibly can’t assume one good end result means the subsequent will maintain up, which is one more reason each candidate will get checked by itself.
The final row is the essential one. A single agent session is sweet at one-shot reasoning and unhealthy at bugs that span a sequence of steps, the place every step is legitimate and solely the order is incorrect. For these, the agent is not the search software. Its job is to counsel which sequences are value working by way of a stateful take a look at harness. Used that means, it really works nicely. Used as a alternative for the harness, it misses the most costly bugs there are, those that solely present up throughout a sequence.
Protecting it sincere
A couple of habits do a lot of the work of constructing agent findings reliable, and none of them are sophisticated.
Provenance on each artifact: what produced it, with what context, towards which revision. A discovering ought to be one thing you may re-run months later.Determinism the place it counts: one setting, one solution to construct and run, so “reproduces” means the identical factor on each machine, not simply the one the place it was discovered.Norms, not scripts: inform brokers what issues, the invariants and the bar for an actual discovering, as a substitute of a numbered process. Over-scripted brokers break the identical means over-specified exams do, they hold following the steps after the steps cease making sense. A research of repository context recordsdata discovered the identical factor: the additional necessities lowered job success and raised price by over 20%, and the authors advocate conserving context to the minimal necessities.An individual makes the ultimate name: brokers counsel. They do not resolve what’s actual, what’s a replica of a identified concern, or what will get disclosed and when.
The bottleneck moved
AI did not substitute the safety researcher. It moved the work. The time that used to enter arising with and chasing down hypotheses now goes into judging them at scale, together with constructing the oracle, working the triage, conserving the checklist of identified points, and dealing with disclosure.
The bottleneck did not go away. It moved from discovering bugs to trusting the outcomes, which is a greater place for it, as a result of that is the place human judgment really issues. Nevertheless it’s nonetheless a bottleneck, and ignoring that’s how you find yourself delivery a incorrect “it is high-quality.”
The practices that make this work aren’t new. Reproducible failures, actual oracles, and cautious triage are the identical practices that turned fuzzing from a analysis matter into customary observe over the past fifteen years. The instruments are new. The practices aren’t.
How briskly the instruments hold altering is an open query. Nicholas Carlini, cautious and as soon as a skeptic himself, argues the exponential case is value taking significantly, even whereas he retains vast error bars on it. If the technology facet climbs that quick, the judgment facet has to climb with it, or the hole between what will get produced and what really will get verified solely widens.
For the methods Ethereum will depend on, that is the half that issues. Brokers allow us to cowl much more floor than we may by hand. In trade, they ask for extra cautious judgment, throughout a a lot larger pile of confident-sounding claims. That is a commerce value making, so long as you keep in mind that the judgment is the true product.
