RESEARCHInvestigateNEXT 12 MONTHS
Do Agents Still Follow the Rules? Benchmarking Rule Compliance under Agent Context Compaction
arXiv cs.CL — Computation and Language
Factual evidence
What the source reports
Researchers introduced ARCBench to measure how LLM agent context compaction degrades rule compliance in multi-turn environments.
Inspect the evidence
- Inclusion basis
- Enterprise AI
- Publisher and source type
- arXiv cs.CL — Computation and Language · RESEARCH
- Published by source
- 4 November 2026
- Collected by OneBench
- 5 Nov 2026, 02:01 UK
Stored source excerpt
arXiv:2611.03223v1 Announce Type: cross Abstract: LLM agents compact long histories to fit their context windows, but the compacted context must still carry the operating rules…
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.