PREPING: Building Agent Memory without Tasks

Computer Science > Artificial Intelligence [Submitted on 11 May 2026] PREPING: Building Agent Memory without Tasks Yumin Choi, Sangwoo Park, Minki Kang, Jinheon Baek, Sung Ju Hwang Agent memory is typically constructed either offline from curated demonstrations or online from post-deployment interactions. However, regardless of how it is built, an agent faces a cold-start gap when first introduced to a new environment without any task-specific experience available. In this paper, we study pre-task memory construction: whether an agent can build procedural memory before observing any target-environment tasks, using only self-generated synthetic practice. Yet, synthetic interaction alone is insufficient, as without controlling what to practice and what to store, synthetic tasks become redundant, infeasible, and ultimately uninformative, and memory further degrades quickly due to unfiltered trajectories. To overcome this, we present Preping, a proposer-guided memory construction framework. At its core is proposer memory, a structured control state that shapes future practice. A Proposer generates synthetic tasks conditioned on this state, a Solver executes them, and a Validator determines which trajectories are eligible for memory insertion while also providing feedback to guide future proposals. Experiments on AppWorld, BFCL v3, and MCP-Universe show that Preping substantially improves over a no-memory baseline and achieves performance competitive with strong playbook-based methods built from offline or online experience, with deployment cost 2.99\times lower on AppWorld and 2.23\times lower on BFCL v3 than online memory construction. Further analyses reveal that the main benefit does not come from synthetic volume alone, but from proposer-side control over feasibility, redundancy, and coverage, combined with selective memory updates. Comments: Preprint Subjects: Artificial Intelligence (cs.AI); Computation and Language (cs.CL) Cite as: arXiv:2605.13880 [cs.AI]   (or arXiv:2605.13880v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2605.13880 Focus to learn more Submission history From: Yumin Choi [view email] [v1] Mon, 11 May 2026 04:34:43 UTC (1,166 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-05 Change to browse by: cs cs.CL References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)