paper-with-me

홈 › Papers

Fault-Tolerant Sandboxing for AI Coding Agents: A Transactional Approach to Safe Autonomous Execution

2025-12-14 · Boyang Yan arxiv

The transition of Large Language Models (LLMs) from passive code generators to autonomous agents introduces significant safety risks, specifically regarding destructive commands and inconsistent system states. Existing commercial solutions often prioritize interactive user safety, enforcing authentication barriers that break the headless loops required for true autonomy. This paper presents a Fault-Tolerant Sandboxing framework designed to mitigate these risks through a policy-based interception layer and a transactional filesystem snapshot mechanism. We hypothesize that wrapping agent actions in atomic transactions can guarantee safety with acceptable latency, outperforming the heavy initialization overhead of containers or the interactive friction of commercial CLIs. We validated this approach by deploying the Minimind-MoE LLM served via nano-vllm on a custom Proxmox-based testbed utilizing EVPN/VXLAN isolation. Experimental results demonstrate a 100\% interception rate for high-risk commands and a 100\% success rate in rolling back failed states. Crucially, our prototype incurs only a 14.5\% performance overhead (approx. 1.8s) per transaction. In contrast, benchmarking against the Gemini CLI sandbox revealed that it requires interactive authentication ("Sign in"), rendering it unusable for headless, autonomous agent workflows.

📄 PDF Abstract BibTeX arXiv:2512.12806

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Reinforcement Learning Decoders for Fault-Tolerant Quantum Computation

2018-10-16 · Ryan Sweke, Markus S. Kesselring, Evert P. L. van Nieuwenburg, Jens Eisert

Topological error correcting codes, and particularly the surface code, currently provide the most feasible roadmap towards large-scale fault-tolerant quantum computation. As such, obtaining fast and flexible decoding alg…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Distributed Agent System: Fault-Tolerant Collaboration Among Embodied Agents

2026-07-12 · Kai Yu, Lu Chen, Hanqi Li arxiv

AI engineering is shifting from passive text generation by large language models (LLMs) to agent-driven task execution, creating new reliability challenges for long-horizon tasks under resource constraints and environmen…

Text Generation

Decentralized Federated Policy Gradient with Byzantine Fault-Tolerance and Provably Fast Convergence

2024-01-07 · Philip Jordan, Florian Grötschla, Flint Xiaofeng Fan, Roger Wattenhofer

In Federated Reinforcement Learning (FRL), agents aim to collaboratively learn a common task, while each agent is acting in its local environment without exchanging raw trajectories. Existing approaches for FRL either (a…

Deep neural decoders for near term fault-tolerant experiments

2018-02-18 · Christopher Chamberland, Pooya Ronagh

Finding efficient decoders for quantum error correcting codes adapted to realistic experimental noise in fault-tolerant devices represents a significant challenge. In this paper we introduce several decoding algorithms c…

Fault Tolerant Equilibria in Anonymous Games: best response correspondences and fixed points

2020-05-14 · Deepanshu Vasal, Randall Berry

The notion of fault tolerant Nash equilibria has been introduced as a way of studying the robustness of Nash equilibria. Under this notion, a fixed number of players are allowed to exhibit faulty behavior in which they m…