RESEARCHInvestigateNEXT 12 MONTHS
Empty Commitments: When Agents Promise What They Cannot Deliver
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
Researchers identify empty commitments in LLM agents, where models promise future actions unsupported by their runtime configuration.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.CL — Computation and Language · RESEARCH
- Published by source
- 9 October 2026
- Collected by OneBench
- 10 Oct 2026, 03:01 UK
- Original headline
- Empty Commitments: When Agents Promise What They Cannot Deliver ↗
Stored source excerpt
arXiv:2610.01045v2 Announce Type: replace-cross Abstract: A chatbot that says "I will remind you tomorrow" will not run again until the user writes. We call such…
Short excerpt from the collected text, not the full source. Use the source link to read it in context.
The factual summary is a OneBench synthesis, not a quotation or independent verification. Collection time is not publication time. Open the source for its full context; related reporting can share the same underlying announcement.