arXiv (OAI Expanded)
open access
BLINDSPOT: A Benchmark for Safety and Refusal Calibration in Long-Horizon Tool-Using Agents
and-sciencecomputation-and-languagecomputational-engineeringfinancemachine-learningmultiagent-systems
Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and external environment feedback. In such settings, safety failures may emerge only after multiple turns, yet existing evaluations often reduce agent b
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- Agent Safety From Within: Detecting Harmful Trajectories from LLM Internal States#1117751
- Benchmarking large language model agent societies against human behavioural distributions#784936
- Benchmarking large language model agent societies against human behavioural distributions#783346
- Embodied Agents Take Control: Minimal-Interface Zero-Shot Agents Rival Industrial-Scale Policies in Vision-and-Language Navigation#1035572
- Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense#973202
Record · ID 1110671
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive