Subject

Agent safety

3 open-access journal articles on agent safety, published in 2026 in Life of Research. Every record is free to read and download, with a permanent link and a ready-made citation.

3 records

Journal article

Checked at Every Step Is Not Checked as a Whole: Two Senses of Plan-Level Safety for LLM Agents, and Why Decomposition Attacks Exploit the Gap Between Them

Pranay Mahendrakar 2026

Most deployed safety mechanisms for LLM agents judge one unit at a time: a single tool call, or a single (observation, action) pair (Choi et al., 2026). A separate literature asks whether that is the right unit to judge at all. Jones, Dragan and Steinhardt (2024) show that a task no single…

Cite Related research LOR-00054 · 11 views · 41 downloads

PDF6 MB

Journal article

Not Acting Is Not One Decision: Two Abstention Triggers in Tool-Using Agents, Why the Calibration and Permission Readings Cover Different Ones, and the Cost Term Neither Supplies

Pranay Mahendrakar 2026

An agent that declines to send the email has made a decision that looks like the decision a language model makes when it declines to answer a question, and the resemblance has organised the 2026 literature into two camps. One reads not-acting as a calibration problem: the agent should estimate its…

Cite Related research LOR-00018 · 8 views · 23 downloads

PDF537.1 KB

Journal article

Ordering Is Not Resolution: What the Instruction Hierarchy Defines, What It Leaves Undefined, and the Same-Tier Conflicts Agent Benchmarks Do Not Separate

Pranay M. Mahendrakar 2026

When a language-model agent receives instructions that conflict, the dominant remedy is a privilege ordering over sources: system above developer, developer above user, user above tool output. This paper argues that the ordering paradigm is well-defined for one class of conflict and undefined for…

Cite Related research LOR-00042 · 6 views · 16 downloads

PDF407.9 KB

Cite

APA

BibTeX

Import into a reference manager: BibTeX · RIS (Zotero, Mendeley, EndNote)