model-checking

Tag

Cards List
#model-checking

Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement

arXiv cs.AI · 6d ago Cached

This survey paper reviews 38 studies on safe LLM agents, highlighting key challenges such as specification translation bottlenecks, incomplete safety guarantees from enforcement methods like runtime monitoring, and the verifier tax that impedes safe task completion.

0 favorites 0 likes
#model-checking

Improving system safety with Temporal Logic of Actions (TLA+)

Lobsters Hottest · 2026-08-15 Cached

TLA+ is a model checking tool that explores all state interleavings to find bugs in distributed systems; it helped improve safety in Depot Registry's garbage collector by identifying a missed bug through formal verification.

0 favorites 0 likes
#model-checking

Specula: Scaling formal specifications for autonomous model checking of system code (13 minute read)

TLDR AI · 2026-08-13 Cached

Specula is an agentic system that automatically derives TLA+ specifications from code, runs model checking to find concurrency bugs, and reproduces them via integration tests. It found 249 bugs across 48 open-source distributed and concurrent systems, demonstrating a significant scaling of formal verification.

0 favorites 0 likes
#model-checking

Kani: A Model Checker for Rust

Hacker News Top · 2026-07-06 Cached

Kani is an open-source model checker for Rust that uses bounded model checking on the MIR to verify safety properties and functional correctness, with a specification language for unbounded verification. The paper reports case studies on industrial Rust projects where Kani uncovered six previously unknown bugs and operates at scale in production CI.

0 favorites 0 likes
#model-checking

Intro to TLA+ for the LLM Era: Prompt Your Way to Victory

Hacker News Top · 2026-05-17 Cached

An introduction to using TLA+ with LLMs like Claude to write formal specifications, showing how LLMs can help with syntax while focusing on correctness.

0 favorites 0 likes
#model-checking

Synthesizing POMDP Policies: Sampling Meets Model-checking via Learning

arXiv cs.AI · 2026-05-15 Cached

This paper presents a novel framework for synthesizing finite-state controllers for Partially Observable Markov Decision Processes (POMDPs) by integrating sampling, automata learning, and model-checking. The approach provides formal guarantees for threshold-safety problems that elude existing formal synthesis tools.

0 favorites 0 likes
#model-checking

Can LLMs model real-world systems in TLA+?

Hacker News Top · 2026-05-08 Cached

Researchers from the Specula team created SysMoBench, a benchmark evaluating whether LLMs can faithfully model real-world computing systems in TLA+ or merely recite textbook specifications. The benchmark tests 11 systems across four phases and reveals systematic gaps in current LLMs' ability to accurately model system implementations versus reference papers.

0 favorites 0 likes
#model-checking

People get confused when language implementations break language guarantees

Hillel Wayne — Computer Things · 2026-04-21 Cached

TLA+ semantics guarantee nonordered updates, but the TLC model checker breaks these guarantees by requiring ordered assignments and adding effectful operators like PrintT, causing confusion for beginners.

0 favorites 0 likes
#model-checking

Proving What's Possible

Hillel Wayne — Computer Things · 2026-02-11 Cached

Explains the concept of possibility properties in formal methods, complementing safety and liveness, and discusses their use in specification and model checking.

0 favorites 0 likes
← Back to home

Submit Feedback