{"ID":3083903,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T07:23:37.79250861Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05894","arxiv_id":"2606.05894","title":"EMBER: Efficient Memory via Budgeted Evidence Retention for Long-Horizon Agents","abstract":"Long-horizon agents can archive large histories, but future answers still incur retrieval, rereading, and context costs. When retained memory misses answer-relevant evidence, the system must return to larger portions of the raw history. We study budgeted evidence survival: before the query is known, which source evidence should be retained so that it remains recoverable and usable under a fixed retained source-evidence token budget? We instantiate this setting as Budgeted Pre-Query Retention, where memory is written during ingestion and later read without access to the full raw stream. We introduce EMBER, a learned retention policy that constructs a compact, source-backed evidence state. EMBER stores evidence capsules: verbatim source excerpts paired with retrieval keys and update metadata, preserving both grounding and read-time access. Post-query outcome feedback trains the writer to preserve evidence across the ingestion-retrieval-answer chain. On LongMemEval-RR, our LongMemEval-derived retained-evidence protocol, EMBER-14B reaches 0.3017 F1 at the 8192-token retained-evidence comparison point, compared with 0.1765 for the strongest non-EMBER budgeted baseline. Across retained source-evidence budgets, EMBER improves F1, Retain-Recall, and Read-Recall, indicating that long-horizon memory depends on retaining evidence within the budget rather than rereading larger histories.","short_abstract":"Long-horizon agents can archive large histories, but future answers still incur retrieval, rereading, and context costs. When retained memory misses answer-relevant evidence, the system must return to larger portions of the raw history. We study budgeted evidence survival: before the query is known, which source eviden...","url_abs":"https://arxiv.org/abs/2606.05894","url_pdf":"https://arxiv.org/pdf/2606.05894v1","authors":"[\"Yilong Li\",\"Suman Banerjee\",\"Tong Che\"]","published":"2026-06-04T09:03:05Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[]","has_code":false}