arxiv:2609.15134
Published on Sep 14
· Submitted by
YunHao-Feng on Sep 15
Upvote
18
Authors:
,
,
,
,
,
,
,
Abstract
HazardAuditor provides execution-grounded safety supervision for computer-use agents and introduces Guard Policy Optimization to align generative guard training with sequence-level safety outcomes.
Generated by thinkingmachines/Inkling-Small
Computer-use agents increasingly interact with browsers, terminals, file systems, and external services, introducing safety risks that emerge through runtime behavior rather than generated content alone. Existing guard models target static prompts and responses and are poorly suited to agent execution; existing executable safety platforms produce evaluation verdicts rather than the normalized supervision a guard model needs to learn across heterogeneous agent frameworks. We introduce HazardAuditor, an execution-grounded framework that closes both gaps. Its infrastructure runs heterogeneous agents (Claude Code, Codex, Hermes, and OpenClaw) in controlled environments and normalizes their interactions into a canonical event representation for cross-framework supervision. We further observe that token-level post-training objectives create a structural mismatch for generative guards, causing longer rationales to dominate gradient updates. Guard Policy Optimization (GuardPO) addresses this by converting deterministic safety outcomes into sequence-level advantages and normalizing rationale and verdict regions, making the safety decision the effective unit of optimization. Across multiple benchmarks and heterogeneous computer-use systems, HazardAuditor improves accuracy by up to 16.5 percentage points over the strongest prior guard. Code, models, and evaluation artifacts will be available at https://yunhao-feng.github.io/HazardAuditor/.
View arXiv page View PDF Project pageGitHub 20 Add to collection
Community
Paper submitter 8 days ago
A comprehensive multi-framework guard model with cot.
7 days ago
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
-
RePolicy: Reinforcement Learning for Safety-Policy Invocation in Agent Safeguards (2026)
-
Reassembling Distributed Risk: Trajectory-Conditioned Action Generation for Multi-Turn Agent Safety (2026)
-
SynChain: Inducing Computer-Use Agent Systems to Construct Their Own Attack Chains (2026)
-
Beyond Handcrafted Security: Towards Self-Evolving Defense for LLM Agents (2026)
-
LatentGuard: Efficient and Inspectable Latent Reasoning for LLM Safeguards (2026)
-
AgentS4D: Benchmarking Runtime Risks across the Execution Lifecycle of LLM-Based Workspace Agents (2026)
-
ToolGuardian: Declarative Security for AI Agent-Tool Interactions (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on HF Mirror checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment: @librarian-bot recommend
Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.
Tap or paste here to upload images
· Sign up or log in to comment
Upvote
18
Get this paper in your agent:
hf papers read 2609.15134
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 1
Datasets citing this paper 0
No dataset linking this paper
Cite arxiv.org/abs/2609.15134 in a dataset README.md to link it from this page.
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2609.15134 in a Space README.md to link it from this page.
Collections including this paper 0
No Collection including this paper
Add this paper to a collection to link it from this page.