Posts

While multi-agent programming solves context limitations and enables complex tasks, it introduces a critical risk of race conditions. Agents operating on stale contexts may generate incorrect patches or overwrite each other’s changes. This conflict often results in infinite modification loops as agents repeatedly attempt to fix errors introduced by concurrent edits on intertwined code. Consequently, the efficiency of multi-agent programming is seriously degraded. To address this problem, we propose a reader-writer lock mechanism to prevent race conditions.

Unlike 2–3 years ago, a prompt can now be considered an executable program. This is because an agent can access local files and execute simple programs on its own. Furthermore, agents can fetch prompts on their own based on the tasks they are given. This means we cannot statically determine which prompt will be executed. For instance, if we instruct an agent to review code, the agent may fetch the ‘how-to-review-code.

My first project was Synstiller, which aimed to build an interpretable coding model. Over nearly a year and a half, I invested substantial effort to solve the problem, but I did not achieve clear results. However, knowing I did my best allowed me to let go with confidence, teaching me that doing my best is the key to moving on without regret. After that, I worked on a project called VeriSafe Agent, which verifies an agent’s behavior from a program verification perspective.