AI RESEARCH
Compress the Context, Keep the Commitments: A Formal Framework for Verifiable LLM Context Compression
arXiv CS.LG
•
ArXi:2605.17304v1 Announce Type: new LLM context is not just tokens; it is a set of commitments. Long-running conversations accumulate goals, constraints, decisions, preferences, tool results, retrieved evidence, artifacts, and safety boundaries that future responses must preserve. Existing context-management methods reduce length through truncation, retrieval, summarization, memory systems, or token-level prompt compression, but they rarely specify which semantic commitments must survive compression or how their preservation should be measured.