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

2026-04-30 · Tianyuan Wu, Chaokun Chang, Lunxi Cao, Wei Gao, Wei Wang arxiv

Autonomous agents act through sandboxed containers and microVMs whose state spans filesystems, processes, and runtime artifacts. Checkpoint and restore (C/R) of this state is needed for fault tolerance, spot execution, RL rollout branching, and safe rollback-yet existing approaches fall into two extremes: application-level recovery preserves chat history but misses OS-side effects, while full per-turn checkpointing is correct but too expensive under dense co-location. The root cause is an agent-OS semantic gap: agent frameworks see tool calls but not their OS effects; the OS sees state changes but lacks turn-level context to judge recovery relevance. This gap hides massive sparsity: over 75% of agent turns produce no recovery-relevant state, so most checkpoints are unnecessary. Crab (Checkpoint-and-Restore for Agent SandBoxes) is a transparent host-side runtime that bridges this gap without modifying agents or C/R backends. An eBPF-based inspector classifies each turn's OS-visible effects to decide checkpoint granularity; a coordinator aligns checkpoints with turn boundaries and overlaps C/R with LLM wait time; and a host-scoped engine schedules checkpoint traffic across co-located sandboxes. On shell-intensive and code-repair workloads, Crab raises recovery correctness from 8% (chat-only) to 100%, cuts checkpoint traffic by up to 87%, and stays within 1.9% of fault-free execution time.

📄 PDF Abstract BibTeX arXiv:2604.28138

Code (0)

등록된 구현이 없습니다.

CRAB: Class Representation Attentive BERT for Hate Speech Identification in Social Media

2020-10-25 · Sayyed M. Zahiri, Ali Ahmadvand

In recent years, social media platforms have hosted an explosion of hate speech and objectionable content. The urgent need for effective automatic hate speech detection models have drawn remarkable investment from compan…

Hate Speech Detection Sentence

Ranking Neural Checkpoints

2020-11-23 · CVPR 2021 1 · Yandong Li, Xuhui Jia, Ruoxin Sang, Yukun Zhu 외

This paper is concerned with ranking many pre-trained deep neural networks (DNNs), called checkpoints, for the transfer learning to a downstream task. Thanks to the broad use of DNNs, we may easily collect hundreds of ch…

Transferability Transfer Learning

DART: Semantic Recoverability for Structured Tool Agents

2026-05-22 · Ke Yang, Panpan Li, Zonghan Wu, Kejin Xu 외 arxiv

When a structured tool agent fails mid-execution, the runtime faces a dilemma: replaying the entire task is safe but wasteful, while restoring from a local checkpoint is efficient but can leave committed downstream work …

Proof-Carrying Agent Actions: Model-Agnostic Runtime Governance for Heterogeneous Agent Systems

2026-06-02 · Zexun Wang arxiv

Agent systems execute through runtimes with very different control points: local coding tools, framework SDKs, managed agent platforms, API gateways, and observer-only integrations. A high-risk action such as publishing …

Execution-State Capsules: Graph-Bound Execution-State Checkpoint and Restore for Low-Latency, Small-Batch, On-Device Physical-AI Serving

2026-06-18 · Liang Su arxiv

Mainstream LLM serving systems reuse prefix work mainly through paged or radix key-value (KV) caches. This is highly effective for high-throughput, high-concurrency serving, but it manages only one positional fragment of…