pith. sign in

Title resolution pending

immediately emits a normalizedtool_callaction viaActionSink

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

1 Pith paper citing it
browse 1 citing papers

Title metadata for this work has not finished resolving. The hub is built from the citation graph; the title resolver retries DOI and OpenAlex on its next pass.

fields

cs.CL 1

years

2026 1

verdicts

UNVERDICTED 1

representative citing papers

Auditing Agent Harness Safety

cs.CL · 2026-05-14 · unverdicted · novelty 7.0 · 2 refs

HarnessAudit audits full execution trajectories of LLM agents for boundary compliance and introduces HarnessAudit-Bench showing that task completion often diverges from safe execution with risks accumulating over longer trajectories.

citing papers explorer

Showing 1 of 1 citing paper.

  • Auditing Agent Harness Safety cs.CL · 2026-05-14 · unverdicted · none · ref 13 · 2 links

    HarnessAudit audits full execution trajectories of LLM agents for boundary compliance and introduces HarnessAudit-Bench showing that task completion often diverges from safe execution with risks accumulating over longer trajectories.