AI Agents Found to Share Arithmetic Results via Hidden Workspace Storage

iconCryptoSlate
Share
AI summary iconSummary
A Nov. 9 preprint showed AI agents can share arithmetic results via hidden workspace storage in the crypto market. Tampere University researchers found agents using shared storage could access each other’s work without direct collaboration. Testing with GPT-6 Astra showed 49 out of 50 trials succeeded when agents rechecked the workspace. altcoins to watch may benefit from such AI advancements. Success rates dropped without the recheck instruction, highlighting risks of unintended data sharing.

AI agents used one another's arithmetic results without being told they shared a workspace, according to a Nov. 9 preprint.

Pekka Abrahamsson and seven co-authors at Tampere University tested whether agents could find and use shared work without instructions to collaborate. Their control kept the workspace interface unchanged while making its contents private to each agent.

Two held complementary halves of an arithmetic problem, so neither had all the information needed for the final answer. Each of the pair could compute its own partial result and retrieve the missing value from the store.

The other two received self-contained tasks. Agents could list stored keys, read or write values, and submit an answer within 20 steps.

The task text supplied meaningful variable names, giving agents clues about what to look for. Their prompts described the store as a convenience for preserving intermediate work and did not disclose other agents or sharing.

In a preregistered extension with a workspace-recheck instruction, OpenAI's GPT-6 Astra achieved joint success in 49 of 50 shared-store trials in the reference implementation and 47 of 50 in a second implementation.

Related Company OpenAI AI research and deployment company

Joint success meant both agents with interdependent tasks submitted the correct answer.

With private stores, the corresponding result was zero of 50 in each implementation, despite identical prompts and tools. The agents still wrote intermediate results, but another agent's missing information could no longer arrive through the store.

Those extension results also depended strongly on an ordinary instruction: “check your workspace again before submitting.” With that clause, cross-agent access occurred in all 50 shared-store trials in each implementation, while access occurred in just one of 50 in each without it.

Joint success without the clause was 1 of 50 and zero of 50, respectively. Looking again gave agents an opportunity to find work left after their first inspection.

Change the tested condition

Shared store with the workspace-recheck clause: both paired agents answered correctly in 49/50 and 47/50 trials.

Shared state carried useful information. Intent to communicate was not established.

Controlled four-agent arithmetic with task-supplied variable names. Same-group implementation replication; results do not measure deployment frequency.

Reading someone else's value can include an accidental collision between storage keys. The private-store comparison supports the conclusion that shared information helped solve the paired tasks.

The second implementation was built independently from a written protocol by a co-author in the same research group.

The paper records a limit to that independence: early results from a differently worded replication reached the original experimenter before most reference data collection. Measured behavior also varied with models and implementation choices.

The small arithmetic setting and task-supplied keys limit the results' generalizability.

The mechanism differs from a recent memory-safety study, which concerned remembered permission carrying into later simulated tasks. Here, separate agents obtained information through shared workspace state.

The authors recommend treating shared caches, scratch directories, and memory services as communication channels: separate them where sharing is unintended, use namespaces where appropriate, and log authorship.

Disclaimer: The information on this page may have been obtained from third parties and does not necessarily reflect the views or opinions of KuCoin. This content is provided for general informational purposes only, without any representation or warranty of any kind, nor shall it be construed as financial or investment advice. KuCoin shall not be liable for any errors or omissions, or for any outcomes resulting from the use of this information. Investments in digital assets can be risky. Please carefully evaluate the risks of a product and your risk tolerance based on your own financial circumstances. For more information, please refer to our Terms of Use and Risk Disclosure.