pith. sign in

Toolformer: Language models can teach themselves to use tools

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.CR 1

years

2026 1

verdicts

CONDITIONAL 1

representative citing papers

Measuring Safety Alignment Effects in Autonomous Security Agents

cs.CR · 2026-05-19 · conditional · novelty 7.0

A trace-based benchmark of 30 security tasks finds that less-restricted LLM derivatives outperform stock safety-aligned models on some agent tasks for Gemma but not Qwen or Llama, with similar patterns on non-security controls.

citing papers explorer

Showing 1 of 1 citing paper.

  • Measuring Safety Alignment Effects in Autonomous Security Agents cs.CR · 2026-05-19 · conditional · none · ref 24

    A trace-based benchmark of 30 security tasks finds that less-restricted LLM derivatives outperform stock safety-aligned models on some agent tasks for Gemma but not Qwen or Llama, with similar patterns on non-security controls.