Instruction Stacking Collapse Benchmark

What is Instruction Stacking Collapse?

A repeatable evaluation of instruction following as multiple verifier-checked constraints accumulate in a prompt.

Released

2026-07-31

Evaluates

Code & Software, Software & AI Compute, cs.SE

Openness

unknown

Importer

Claire Radar

Review status

ai-reviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2608.02639

Instruction Stacking Collapse paper

• Paper https://arxiv.org/abs/2608.02639

Which sources cite Instruction Stacking Collapse?

• Instruction Stacking Collapse

Related Code & Software, Software & AI Compute, cs.SE benchmarks

• Active-SWE
• AFT-Bench
• Agent App Benchmark
• Agent Retrieval Bench
• Agent Systems Benchmark (ASB)
• Agentic Evaluation in 2D Mazes
• Agentic Security Benchmark
• AgentInfraBench