overfeed.news
Anúncio

Agendator

Agendamento online grátis para sua barbearia ou salão.

Página de agendamento, agenda e lembretes por e-mail. Sem cookies nem anúncios para seus clientes.

Criar minha página grátis

Empresa

Anthropic

1.118documentos

101últimos 7 dias

arXiv AI Papers

DoGNAVY-Exploit: Harnessing Parallel Open-Weight Agents for Stage-Aware Vulnerability Exploitation

Frontier LLM agents can turn known vulnerabilities into working exploits, but are costly and often access-restricted due to their potential for malicious use. Open-weight models offer a more accessible alternative, but struggle to maintain progress across long exploitation chains. They also often fail to apply relevant security knowledge at the appropriate stage and in the right context to identify and evaluate promising attack directions. To address these limitations, we propose DoGNAVY-Exploit, a multi-agent harness built around two complementary designs: stage-aware decomposition with progressive expert knowledge disclosure, and hierarchical orchestration with parallel exploration. Specifically, DoGNAVY-Exploit uses configurable milestones to recast long-horizon exploitation as short, verifiable capability transitions and provides only the knowledge relevant to each stage. Within each milestone, a hierarchical architecture separates strategic planning from parallel execution: a planner proposes diverse attack routes, executors test them concurrently, and a controller accepts progress only when supported by runtime evidence. A shared structured memory consolidates verified facts, artifacts, replay steps, and failed routes across branches, allowing agents to build on collective progress and carry validated knowledge into subsequent milestones. In controlled benchmark environments, DoGNAVY-Exploit with GLM-5.2 achieves 97.5% Pass@1 on Cybench, and 97.5% zero-day and 100% one-day Pass@1 on CVE-Bench. On ExploitGym, it solves 79 tasks with GLM-5.2 and 157 with GLM-5.3, while the corresponding public Claude Code baselines solve 39 and 130 tasks, respectively. Ablation results further demonstrate that the stage-aware orchestration, expert knowledge, parallel exploration, and memory designs can substantially improve the exploitation capabilities of open-weight agents.

en
GitHub Releases (AI inference)

ollama v0.40.14

What's Changed ollama launch claude now applies the model's output token limit for Claude Code, so cloud models no longer run into the 128k default cap Cloud web search responses on /api/chat are now decoded correctly, including compressed responses OpenAI-compatible endpoints no longer override a model's packaged sampler defaults — clients that send no temperature/top_p get the model's own values…

en
arXiv AI Papers

DiabAgent: Toward Agentic Physiological Control

As pretraining scales, medical language models have advanced rapidly in clinical question answering. Their ability to achieve effective physiological control through sustained intervention still lacks systematic quantitative evaluation. Type 1 diabetes provides a concrete setting: impaired insulin secretion creates dependence on exogenous insulin, with dosing continually adjusted using information about meals, exercise, illness, and glucose measurements. We introduce DiabAgent, a research suite for agentic physiological control comprising the Agentic Physiological Control (APC) framework, the DiabetSim simulator, and the SweetBench benchmark. APC controls glucose through medical-device tools, using ongoing observations to infer individual states, accumulate personal experience, and choose treatment actions. We build DiabetSim to simulate different patients, events, and device conditions for scalable virtual testing and training. Using DiabetSim, we construct SweetBench by instantiating 32 scenario designs as 212 glucose-control tasks. With Claude Opus 5.5 and a fixed decision interval of one hour, APC achieves a COGI of 73.5, compared with 71.2 for the open-source closed-loop baseline OpenAPS. Ablations further show that individual adaptation and contextual information improve glucose control. Combining high-frequency rule-based control with lower-frequency agent decisions shows potential for balancing control performance and computational cost. Our work provides a framework, simulator, and evaluation foundation for agents to participate in human physiological control.

en
arXiv AI Papers

VeriHarm-Bench: Measuring Harmful Success in LLM Coding Agents Verifiably

Large language model (LLM) coding agents increasingly operate with shell access, allowing them to write scripts, move files, alter permissions, and modify system configurations. However, an agent may achieve a user's goal while causing unintended harm, such as deleting unrelated files, weakening access controls, or corrupting data, in response to benign inputs without explicit jailbreaking. This failure mode is particularly important because apparent task success may reassure users that an agent behaved correctly, causing harmful side effects to go unnoticed. We call this harmful success: the agent successfully completes the intended benign task while simultaneously causing unintended harm. Despite its importance, harmful success is difficult to measure because conventional task-success metrics overlook harmful behaviors, while existing safety evaluations are often designed solely to assess harmful outcomes. We introduce VeriHarm, an automatic framework for constructing programmatically verifiable benchmarks that directly measure harmful success. VeriHarm minimally perturbs coding tasks to elicit unintended harmful behavior while maintaining the benignity of the task and preserving the original task objective. It then synthesizes executable harm tests that, together with the original task-correctness tests, evaluate both task accuracy and harmful outcomes. Frontier agents, including GPT-5.6-Sol and Claude-Opus-5, achieve an average task accuracy of 95% on our curated VeriHarm-Bench, yet still struggle to complete tasks safely: their safe success rate, the fraction of tasks completed successfully without triggering the designated harm, averages only 37%. These results suggest that successful task completion can frequently coexist with unintended harm, and that task-success metrics alone may substantially understate the potential safety risks of coding agents.

en
arXiv AI Papers

MCP Tool Poisoning in Agentic AI Frameworks: A Cross-Framework Measurement Study

The Model Context Protocol (MCP) lets agentic AI frameworks connect language models to external tool providers, but it carries attacker-controlled content (tool descriptions, schema fields, and response data) into model context without validation. Prior benchmarks measure model compliance with poisoned instructions without confirming real execution. We present the first cross-framework measurement of MCP tool poisoning with real tool execution. A 25-class root-cause taxonomy unifies prior classifications, and the open-source tool mcpvenom drives a 9,720-cell susceptibility matrix across 12 frameworks, 18 models, and 45 attack scenarios, with a dual oracle that confirms exfiltration via canary HTTP receipt. The overall attack success rate is 22.9% (2,113 vulnerable cells). Of these, 64.9% dispatch an attacker tool call, 23.0% contact the attacker endpoint, and 12.1% verifiably exfiltrate a secret. Resistance is model-level: nine core frameworks cluster within 23 to 26% (chi-squared = 3.30, p = 0.91), and no framework implements intentional defense. Incidental framework properties mitigate in specific cases, and a regex description scanner rejects 20 of 45 scenarios at a 7.2% false-positive rate, so metadata scanning alone is a partial control. Model ASR ranges from 0.4% to 49.7%. Claude Opus 4.8 is vulnerable in 8 of 530 cells while issuing 223 explicit refusals. A code-level audit finds no intentional defense across twelve frameworks, and all five coordinated disclosures across four vendors were rejected.

en
Anthropic — overfeed.news