Skip to content
Agents

ArbiGraph: Arbitrarily Scalable Verifiable Task Graphs for Evaluating Context Management.

arXiv:2607.20764v2 Announce Type: replace Abstract: We introduce ARBIGRAPH, a benchmark generator for evaluating whether tool-assisted language agents can retain, update, compose, and discard task-relevant context across extended reasoning workflows. ARBIGRAPH

arXiv cs.AIResearch source·