Pith. sign in

REVIEW 6 cited by

AgentCgroup: Understanding and Controlling OS Resources of AI Agents

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2602.09345 v3 pith:GXICICNJ submitted 2026-02-10 cs.OS cs.AI

AgentCgroup: Understanding and Controlling OS Resources of AI Agents

classification cs.OS cs.AI
keywords resourceagentcgroupagentsexecutionmismatchacrosscallsdemands
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

AI agents are increasingly deployed in multi-tenant cloud environments, where they execute diverse tool calls within sandboxed containers, each call with distinct resource demands and rapid fluctuations. We present a systematic characterization of OS-level resource dynamics in sandboxed AI coding agents, analyzing 144 software engineering tasks from the SWE-rebench benchmark across two LLM models. Our measurements reveal that (1) OS-level execution (tool calls, container and agent initialization) accounts for 55-60% of end-to-end task latency; (2) memory, not CPU, is the concurrency bottleneck; (3) memory spikes are tool-call-driven with a up to 15.4x peak-to-average ratio; and (4) resource demands are highly unpredictable across tasks, runs, and models. Comparing these characteristics against serverless, microservice, and batch workloads, we identify three mismatches in existing resource controls: a granularity mismatch (container-level policies vs. tool-call-level dynamics), a responsiveness mismatch (user-space reaction vs. sub-second unpredictable bursts), and an adaptability mismatch (history-based prediction vs. non-deterministic stateful execution). We propose AgentCgroup, an intent-driven eBPF-based resource controller that exploits agents ability to declare resource needs and reconstruct execution strategies, using hierarchical cgroup structures aligned with tool-call boundaries, in-kernel enforcement via sched_ext and memcg_bpf_ops, and runtime-adaptive policies. Preliminary evaluation demonstrates improved multi-tenant isolation and reduced resource waste. AgentCgroup is open-source at https://github.com/eunomia-bpf/agentcgroup

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Sandlock: Confining AI Agent Code with Unprivileged Linux Primitives

    cs.CR 2026-05 unverdicted novelty 7.0

    Sandlock provides an unprivileged Linux process sandbox for AI agents by compiling static policies into kernel rules and delegating runtime decisions to a narrow supervisor.

  2. Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes

    cs.OS 2026-04 unverdicted novelty 7.0

    Crab bridges the agent-OS semantic gap with an eBPF inspector, turn-aligned coordinator, and host engine to deliver 100% recovery correctness while cutting checkpoint traffic up to 87% and adding under 2% overhead.

  3. ParaCell: Paravirtualized Secure Containers with Lightweight Intra-Container Isolation and Intent-Driven Memory Management

    cs.OS 2026-05 unverdicted novelty 6.0

    ParaCell reduces latency by up to 88% in nested setups and saves 35.6% memory on agent workloads via MPK XGates and intent-based Pager compared to PVM, RunV, and HyperAlloc.

  4. VIGIL: Runtime Enforcement of Behavioral Specifications in AI Agent Skills

    cs.CR 2026-06 unverdicted novelty 5.0

    VIGIL introduces a policy language and symbolic evaluation rules to enforce context-aware behavioral specifications on LLM agent traces, achieving over 95% recall and under 10% false positives on real tasks.

  5. Lingering Authority: Revocable Resource-and-Effect Capabilities for Coding Agents

    cs.CR 2026-06 unverdicted novelty 5.0

    PORTICO is a revocable capability reference monitor for coding agents that enforces task contracts via grant-invoke-closure lifecycles and rejects post-closure reuses while preserving task success.

  6. Agentic AI Workload Characteristics

    cs.DC 2026-05 unverdicted novelty 5.0

    Agentic workloads with context caching become decode-dominated with high KV-cache reuse and show tool use shifting from early read/explore to later execute/write phases.