The author built LIMBO around six simulated services, twelve boundary fault modes and a ledger recording every committed effect.
Exactly-once behavior shifts from models to contracts with fault type
Tests across models, agent harnesses and service interfaces show that reasoning can prevent some duplicate writes, but ambiguous failures require contract-level safeguards.
Big Tech
Jiapeng Li
Microsoft
Research Digest··2 min read
Li introduces LIMBO, a deterministic sandbox that tracks committed side effects under realistic service and network faults, and evaluates 25,930 agent episodes.
Why this paper
From Microsoft
In one line
Exactly-once for LLM agents requires tool contracts with idempotency keys; model verification alone fails for in-flight or redelivered writes.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§