This paper argues that the community needs a simulation-driven methodology to systematically discover and prevent agent-induced failures across the data sys-tem stack before facing production incidents, and demonstrates this approach on Execution Control Systems (ECS).
This work presents Aries, a full-stack experimentation framework that separates task semantics from execution configurations, reconstructs cross-component agent trajectories with correlated system telemetry, and exposes stateful tool execution through a consistent interface across heterogeneous sandbox substrates.
Leonid Kondrashov, Hongrui Liu, JooYoung Park et al.· arXiv.org· 1 citation
Modern databases must serve highly variable workloads: short queries that demand low latency and long-running tasks that consume significant resources. Under heavy load, these workloads risk spiraling into metastability, a self-sustaining state of degraded throughput and high latency that persists even after the initial stressor is removed. In this paper, we investigate the design of an Execution Control System (ECS) specifically engineered for metastability resilience.To explore this design space, we developed MESSI, a discrete-event simulator implemented in Go that enables us to replay stress scenarios, visualize the formation of metastable feedback loops, and quantify resource allocation trade-offs. By representing systems as a graph of Logic Nodes and Processors, MESSI captures queueing dynamics, I/O delays, and retry policies at a fine grained level. Our research highlights how conventional management policies can inadvertently trigger metastable failures and demonstrates that principled load shedding and bounded concurrency (via a ticket-based abstraction) are essential for maintaining responsiveness. Our findings provide a roadmap for building performant and predictable ECS that explicitly operate within a safe resilient envelope even under dynamically shifting workloads.
Aleksey Charapko, Murat Demirbas, Matt Broadstone et al.· International Conference on...· 1 citation
Two methodology contributions are presented: a declarative-markdown harness with a small mutation surface, and an auto-research loop in which failure-mode analysis on completed experiments proposes new hypotheses, optionally human-reviewed, that progress through the same experiment workflow.
The results show that agents that build and maintain their own tool libraries, a key element of self-evolving agents, can make industrial LLM systems faster, more reliable, and easier to operate.
Kalle Kujanpää, Ning Liu, S. Alam et al.· arXiv.org· 3 citations
Agentic AI is becoming a systems workload. A delegated goal is not a single prompt-response request; it unfolds as an agentic trajectory through model calls, tool calls, context operations, waits, approvals, recovery actions, and external effects. The trajectory is the smallest unit over which budget, authority, recovery, evidence, and physical cost can be stated without hiding essential state in application convention. Existing managed units still matter. Instructions, processes, requests, and model calls each made a different layer of the stack schedulable, protectable, accountable, recoverable, and optimizable. Agentic trajectories strain these units because state, authority, cost, and side effects span many calls. The stack therefore needs a system-visible unit for such trajectories. This paper calls that unit a managed trajectory and focuses on the contract that gives lower layers a common handle on identity, goals, budgets, placement, memory, authority, effects, evidence, and recovery. From a computer architect's perspective, agentic work is an interface and resource-management problem. The paper develops a stack organization and open research agenda around context hierarchy, protected effects, and metrics for useful work per verified action rather than only tokens per second.
DDBench is introduced, a code-repair benchmark of 60 historical bugs mined from 13 open-source distributed systems, partitioned into three difficulty tiers, isolating the effect of debugging context from model capability.
Yibo Yan, Huijuan Wang, Junzhou He et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
