Paper Readings

What a paper claims, what it measured, and what holds up, cited by arXiv id.

• Paper Readings · 2026-09-05

  EarlyEval explained: stopping agent benchmark runs early

  A reading of arXiv:2609.02783, which trains classifiers to halt agent runs once the outcome is predictable, and what its Table III actually shows.

• Paper Readings · 2026-09-05

  Covert Indirect Prompt Injection (ICoA) explained

  A reading of arXiv:2608.30362, which splits attack success into covert and overt outcomes on AgentDojo and shows the covert share can be engineered.