A Randomized Scheduler with Probabilistic Guarantees of Finding Bugs
Summary
This Microsoft Research paper introduces a randomized scheduling technique designed to provide probabilistic guarantees for uncovering bugs in software systems. Published for the ASPLOS conference, it focuses on systematic fault detection through algorithmic randomness.
View Cached Full Text
Cached at: 05/09/26, 04:36 AM
Similar Articles
On the Reliability of Computer Use Agents
A preprint analyzing why computer-use agents succeed once but fail on repeated executions, attributing unreliability to execution stochasticity, task ambiguity, and behavioral variability, and advocating repeated evaluation and stable strategies.
Tim Davis – Probabilistic engineering and the 24-7 employee
Tim Davis, head of Modular, shares his experience building an autonomous code-writing system called Compound Loop and argues that software development is shifting from deterministic to probabilistic systems, with AI agents enabling a '24-7 employee' model where human operators coordinate rather than type, while roles are splitting between high-leverage positions and lower-value agent-wrangling work.
Pruning Unsafe Tickets: A Resource-Efficient Framework for Safer and More Robust LLMs
This paper introduces a resource-efficient pruning framework that identifies and removes parameters associated with unsafe behaviors in large language models while preserving utility. Using gradient-free attribution and the Lottery Ticket Hypothesis perspective, the method achieves significant reductions in unsafe generations and improved robustness against jailbreak attacks with minimal performance loss.
Skill-RAG: Failure-State-Aware Retrieval Augmentation via Hidden-State Probing and Skill Routing
Skill-RAG is a failure-aware RAG framework that uses hidden-state probing and skill routing to diagnose and correct query-evidence misalignment in retrieval-augmented generation. The approach detects retrieval failures and selectively applies targeted skills (query rewriting, question decomposition, evidence focusing) to improve accuracy on hard cases and out-of-distribution datasets.
Retrieval-Conditioned Topology Selection with Provable Budget Conservation for Multi-Agent Code Generation
This paper introduces RGAO, a retrieval-guided adaptive orchestration framework for multi-agent code generation that dynamically selects topology based on code complexity. It provides a formal budget algebra ensuring provable resource conservation while significantly reducing routing errors compared to baseline methods.