CALIBER: Context-Aware LLM Intelligent Boundary Estimation and Routing

Large language models (LLMs) support increasingly long context windows, yet the amount of context they can reliably use often falls well below their nominal limits and varies substantially across models. Existing long-context evaluations primarily measure synthetic retrieval capacity or aggregate task performance, providing limited guidance for selecting an operational context budget. We propose Context-Aware LLM Inference via Boundary Estimation and Routing (CALIBER), a framework that empirically estimates a model-specific effective context threshold $({\tau }_{\mathrm{eff}})$ and uses it to organize long-context inference. CALIBER measures answer correctness, faithfulness, and consistency risk across context lengths and identifies a conservative boundary based on sustained quality degradation and consistency criteria. It then hierarchically indexes documents into threshold-bounded subcontexts, routes queries to relevant indices, processes selected subcontexts in parallel, and aggregates their partial responses. Across 14 LLMs, CALIBER reveals substantial nominal-to-effective context gaps and, on three frontier models, significantly improves average EQ compared to baselines.