Paper

{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.13017v1</id>\n    <title>Structured Distillation for Personalized Agent Memory: 11x Token Reduction with Retrieval Preservation</title>\n    <updated>2026-03-13T14:21:58Z</updated>\n    <link href='https://arxiv.org/abs/2603.13017v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.13017v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Long conversations with an AI agent create a simple problem for one user: the history is useful, but carrying it verbatim is expensive. We study personalized agent memory: one user's conversation history with an agent, distilled into a compact retrieval layer for later search. Each exchange is compressed into a compound object with four fields (exchange_core, specific_context, thematic room_assignments, and regex-extracted files_touched). The searchable distilled text averages 38 tokens per exchange. Applied to 4,182 conversations (14,340 exchanges) from 6 software engineering projects, the method reduces average exchange length from 371 to 38 tokens, yielding 11x compression. We evaluate whether personalized recall survives that compression using 201 recall-oriented queries, 107 configurations spanning 5 pure and 5 cross-layer search modes, and 5 LLM graders (214,519 consensus-graded query-result pairs). The best pure distilled configuration reaches 96% of the best verbatim MRR (0.717 vs 0.745). Results are mechanism-dependent. All 20 vector search configurations remain non-significant after Bonferroni correction, while all 20 BM25 configurations degrade significantly (effect sizes |d|=0.031-0.756). The best cross-layer setup slightly exceeds the best pure verbatim baseline (MRR 0.759). Structured distillation compresses single-user agent memory without uniformly sacrificing retrieval quality. At 1/11 the context cost, thousands of exchanges fit within a single prompt while the verbatim source remains available for drill-down. We release the implementation and analysis pipeline as open-source software.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CL'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.IR'/>\n    <published>2026-03-13T14:21:58Z</published>\n    <arxiv:comment>6 figures. Code: https://github.com/Process-Point-Technologies-Corporation/searchat</arxiv:comment>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Sydney Lewis</name>\n    </author>\n  </entry>"
}