Papers for

ai engineering teams

Papers whose findings have a practical use for this group, as judged from the abstract. Open a paper to read what it means in practice.

Guardrailed meta-agent loops verify policy and crash recovery in simulations

Guardrailed Meta-Agent Loops: Stress-Testing Policy Pinning, Budget Bounds, and Crash Recovery

Abstract: Self-improving agent workflows create an audit problem when the same controller can change both its behavior and the conditions under which that behavior is judged. We present GuardrailLoop, a simulation-based testbed that makes three operational contracts jointly testable: preservation of human-defined policy, compute accounting at every recorded execution prefix, and recovery of a specified scientific state after crashes. A hash-pinned policy fixes goals, scope, evaluation identity, budget, and release conditions; machine-directed evolution is restricted to a code-owned feature catalog and bounded knobs. The contribution is an executable boundary and an evaluation protocol that separates useful adaptation, state recovery, and repeated execution. In a paired 50-seed 2 x 2 study, round-stage growth changes target attainment by +1.00 and restricted mean compute to target by -56.97 simulated GPU-hours (95% paired-bootstrap interval [-58.91,-54.70]); idle growth has zero measured utility effect. Across 240 enumerated crash injections, all runs recover the defined outcome, but only 210 preserve the normalized trace: 30 pre-commit crashes repeat a planner call. Resource-drift, kill-switch, integrity, and output-guard matrices satisfy their specified checks. These findings show why successful outcome recovery is insufficient evidence of exactly-once execution. They establish conformance within one calibrated deterministic testbed, rather than general safety or real-world self-improvement.

Thu 10 SeptRobotics
The gist
When AI agents try to improve themselves, it can be hard to keep track of what rules they follow and if they behave correctly. The authors created a testing setup called GuardrailLoop that checks if agents stick to human-made policies, properly count computing resources used, and recover from crashes without losing important progress. Their experiments showed this setup can tell the difference between genuine progress and hidden bugs during repeated runs. This helps ensure that self-improving AI processes run reliably in controlled scenarios, but it doesn’t guarantee safety in all real-world cases.
Open → 2609.12216v1

Miles system builds reliable scalable training for large AI models

Miles v0.1: Production-Level Post-Training

Abstract: We present Miles v0.1, a full-stack, production-ready system for frontier post-training. Building upon the clean design of slime, Miles designs each stage of the reinforcement-learning (RL) training loop around a single principle: components should be verified, clean, and customizable. With accuracy, efficiency, reliability, and scalability as first-class goals, Miles aims to make frontier-scale RL accessible to researchers and enterprises alike. This report walks through the system end to end: rollout engines built on SGLang, a trainer with a choice of two backends (NVIDIA Megatron-LM and PyTorch FSDP), and three weight-synchronization transports for different deployment topologies. Beyond full-parameter RL, Miles also supports LoRA RL, on-policy distillation, supervised fine-tuning, and true-on-policy rollout-training alignment, and extends the same architecture to diffusion models. We close with an end-to-end case study: fully asynchronous agentic RL on a GLM-5.2 744B-A40B model over terminal-use coding tasks, running on 64 NVIDIA GB300 GPUs with a median step time of 263 seconds over the first 30 measured steps. Miles is open-sourced at https://github.com/radixark/miles, with the project website at https://miles.radixark.com.

Tue 8 SeptMachine LearningComputation and Language
The gist
Training very large AI models can be complicated and slow. The authors introduce Miles, a complete system designed to make training smarter and bigger AI models easier and more efficient. It focuses on clean, customizable parts that work well together, supporting different training methods and hardware setups. They show how it works by training a very large AI model for coding tasks on many GPUs efficiently. The system is freely available for anyone to use and build upon.
Open → 2609.08368v1