A new arXiv paper (arXiv:2610.00349v1) formalizes fault-tolerant budget conservation for distributed multi-agent delegation, using exclusive escrow credits that move through a delegation DAG to preven…
Formal methods can now be applied in small units of work because specifications can be made executable and used as test oracles while coding agents handle most of the typing, according to a Yovico ana…
Software engineers should stop using LLMs to write implementation logic and instead use them as requirements architects, according to a new essay. The approach involves eliciting requirements, generat…
MAREF Engineering published the first post in a series from its technical whitepaper, detailing a Gray Code governance state machine for multi-agent systems that encodes 10 states in 4 bits with a Ham…
A developer has formalized an agent governance framework using TLA+ and model-checked its safety invariants. The framework, available in the MAREF repo, uses Gray Code state machines to ensure every t…
Specula, a push-button agentic system that uses LLM-based coding agents to autonomously generate TLA+ formal specifications for system code, has found 249 bugs across 48 open-source system projects, i…
A developer designed the AGY Witnessed Admission Fabric v0.1, a fail-closed, OPA-governed Read-Only OT shadow gate that prevents AI agents from executing unverified actions. The system uses Open Polic…
Formal methods consultant Hillel Wayne argues that software engineering earns the title of 'real engineering' due to its rigor, while noting that version control is uniquely sophisticated in software …
Polygraph, a new Claude Code plugin and standalone CLI, uses LLMs to automatically generate formal models of stateful JavaScript code and exhaustively check every reachable state for rule violations, …
Gabriela Moreira, a formal methods expert at Informal Systems, discussed on the InfoQ Engineering Culture Podcast how AI is lowering barriers to formal specification and model-based testing through th…
A developer released TLA+ Process Studio, an open-source tool that uses LLMs to help stakeholders model and discuss business processes as state machines, aiming to improve alignment before coding. The…
Researchers formalized and verified four concurrency anomalies in multi-agent LLM systems, establishing a machine-checked consistency hierarchy from L0 to L4. They implemented verified detectors and r…
MAREF, an agentic AI platform, uses TLA+ formal verification to mathematically prove safety invariants in its governance state machine, rather than relying solely on testing. The approach exhaustively…
The article distinguishes between two types of abstraction in system design: modularity abstraction, which hides internal details behind interfaces to simplify usage, and modeling abstraction, which r…
Here is a 2-3 sentence factual summary of the article: SysMoBench is a benchmark designed to evaluate generative AI's ability to formally model complex concurrent and distributed systems using TLA+. …
The article explains that while the accidental complexity of TLA+ (its syntax and tooling) is diminishing due to LLMs, the intrinsic challenge of "modeling judgment"—knowing what to abstract and ignor…
The article explains how token bucket algorithms can prevent retry storms in distributed systems by stopping retries when a downstream service fails. It warns that implementing this algorithm in a seq…
Recent breakthroughs in AI have enabled it to autonomously generate accurate formal specifications from large production codebases, as demonstrated when GitHub Copilot produced precise TLA+ specificat…