Notes from the Ethereum Basis’s Protocol Safety crew on working coordinated AI brokers in opposition to actual protocol code, together with how we arrange the work, what holds up below scrutiny, and what shopper groups and safety researchers can take from it. This publish 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 in opposition to the sorts of methods the community is determined by, 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, mounted 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 actual bugs from those that simply regarded actual.
This publish is for shopper groups and safety researchers who need 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 maintain the outcomes reliable.
Groups elsewhere are converging on the identical recipe. Anthropic’s Frontier Pink Group constructed an agent that writes property-based checks and located actual bugs throughout the Python ecosystem. Cloudflare ran a frontier mannequin via a security-research harness in opposition to 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 actual 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 a couple of weeks. So this publish is intentionally concerning the strategies, that are persistent, reasonably than the tooling. Disclosure is its personal matter and can most likely be its personal publish.
An agent pointed at a codebase is a search device, rather a lot like a fuzzer. The distinction is what comes again. A fuzzer palms you a crash and a stack hint. An agent palms you much more, together with a write-up (name chain, influence declare, advised severity) and the artifacts to again it, like a proof-of-concept you possibly can run in opposition to the actual code.
All of that makes the consequence straightforward to learn and straightforward to belief, the working proof-of-concept most of all. So do not rely what number of candidates an agent produces. Depend what number of transform actual.
How the work is organized
We run many brokers in parallel in opposition to one goal. They coordinate via 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 received this method from Anthropic’s writeup on constructing a C compiler with a fleet of brokers, which coordinates the identical approach. There is no central coordinator to construct or preserve, and fewer that may go mistaken.
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 discipline is trusted previous this level; here is the property it ought to maintain, the way in which it would break, and the proof that may settle it.”Searching takes one speculation, traces the code path, and tries to construct a reproducer.Hole-filling appears to be like at what was accepted and what was rejected, writes the following batch of hypotheses, and tracks protection so the brokers do not maintain 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 appears to be like like earlier than it counts as a discovering:
invariant: the property that should maintain
mechanism: the particular approach it may be made to break
success: observable proof: a panic, a stall, an accepted-invalid enter
reproducer: a self-contained artifact that runs in opposition to the actual code
dedup: a key, so two brokers do not chase the identical factor
The schema is there for a purpose. It forces a particular, testable declare and a transparent definition of completed. An agent that has to put in writing down an observable proof cannot fall again on “this appears to be like dangerous.”
Reproducible or it did not occur
One rule issues greater than every other. A candidate is not a discovering till there is a self-contained artifact that reproduces the failure in opposition to the actual 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 time and again, and each is the agent getting a cross for the mistaken purpose:
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 appears to be like like a crash, however it is not one.A reproducer that builds some inner worth by hand, one no actual enter might ever produce, as a result of each path an attacker controls rejects it earlier. The bug solely “reproduces” in opposition to a perform that nothing reachable calls that approach.In formal-verification work, a proof that goes via however doesn’t suggest what you needed. 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 happy, however the theorem does not constrain the conduct you really cared about.
None of that is new. It is the identical factor as a check that passes as a result of it does not really verify something. What’s new is the amount. An agent writes the ineffective model as quick as the actual one, and simply as confidently. So the verify needs to be automated. You possibly can’t rely on the agent to catch itself.
Sign-to-noise is many of the work
Most candidates are mistaken, duplicate, or out of scope. That is not an issue with the tactic; that is the way it works. The objective is to reject the mistaken ones quick and again the actual 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 may be very completely different from one which wants particular entry or an enormous quantity of assets.
All the pieces will get checked in opposition to a working listing of what is already recognized, mounted, or rejected. With out that, the brokers maintain rediscovering the identical closed challenge and reporting it repeatedly.
Acceptance charges fluctuate rather a lot from goal to focus on, and that variation is beneficial by itself. Run this in opposition to mature, closely audited code and nearly nothing survives, which remains to be price figuring out. “We regarded arduous and located nothing” is an actual consequence. Run it in opposition to less-explored code, or in opposition to formally verified code, the place a machine-checked proof covers a mannequin and the deployed bytecode is simply assumed to match it, and extra will get via.
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 stories, then used rating and knowledgeable evaluate to get all the way 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 particular goal, they’d say extra concerning the goal than concerning the technique.
What the brokers are good at, and the place they mislead
There’s hype in each instructions, so here is a plain listing of what the brokers do properly and the place they mislead.
The break up is not even regular from one process to the following. Stanislav Fort, testing a spread 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 consequence means the following will maintain up, which is another excuse each candidate will get checked by itself.
The final row is the necessary one. A single agent session is nice 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 mistaken. For these, the agent is not the search device. Its job is to recommend which sequences are price working via a stateful check harness. Used that approach, it really works properly. Used as a alternative for the harness, it misses the costliest bugs there are, those that solely present up throughout a sequence.
Retaining it sincere
Just a few habits do many of the work of creating agent findings reliable, and none of them are difficult.
Provenance on each artifact: what produced it, with what context, in opposition to which revision. A discovering needs to be one thing you possibly can re-run months later.Determinism the place it counts: one surroundings, one method 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 an alternative of a numbered process. Over-scripted brokers break the identical approach over-specified checks do, they maintain following the steps after the steps cease making sense. A research of repository context information discovered the identical factor: the additional necessities lowered process success and raised price by over 20%, and the authors advocate preserving context to the minimal necessities.An individual makes the ultimate name: brokers recommend. They do not resolve what’s actual, what’s a reproduction of a recognized challenge, 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, preserving the listing of recognized 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 mistaken “it is nice.”
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 normal observe over the past fifteen years. The instruments are new. The practices aren’t.
How briskly the instruments maintain altering is an open query. Nicholas Carlini, cautious and as soon as a skeptic himself, argues the exponential case is price taking significantly, even whereas he retains large 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 is determined by, that is the half that issues. Brokers allow us to cowl way more floor than we might by hand. In change, they ask for extra cautious judgment, throughout a a lot greater pile of confident-sounding claims. That is a commerce price making, so long as you keep in mind that the judgment is the actual product.
