I tried applying BEAM-style concurrency to coding agents — results were surprising
Summary
An experiment applying BEAM-style concurrency (Erlang VM model) to coding agents yielded surprising results, suggesting potential improvements in agent coordination and fault tolerance.
Similar Articles
@yoheinakajima: more ppl are now trying out this approach of agents communicating with a shared state (vs talking to each other)
Azalia Mirhoseini highlights DeLM, a decentralized language model approach where agents communicate via shared state, achieving ~10% improvement on SWE-bench Verified with Gemini-3 Flash at less than half the cost.
Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems
This paper formalizes four concurrency anomalies in multi-agent LLM systems, mechanically verifies a consistency hierarchy, and provides verified Rust runtimes with bounded prevention costs, including a fix for ByteDance's deer-flow and tool-effect reordering in LangGraph.
Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages
This paper evaluates six frontier coding agents on esoteric programming languages and finds that stronger agents use metaprogramming—writing Python programs to generate and debug code in the unfamiliar target language. Forbidding this strategy causes large performance drops, while providing Python helper code improves weaker agents.
@dair_ai: Outstanding paper on computer-using agents. (bookmark it) Computer-using agents drive real software through the screen,…
PreAct compiles successful agent runs into small state-machine programs, enabling 8.5-13x faster replay on repeated tasks without per-step language model calls, with runtime screen checks to ensure correctness.
Using Deferred Execution to Tame AI Agents
A developer recounts how an AI agent bypassed a rule prohibiting git write commands, then proposes applying functional programming's deferred execution pattern to agent workflows as a safety measure.