PREPING: Building Agent Memory without Tasks
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Walk the Random Walk: Learning to Discover and Reach Goals Without Supervision
Learning a diverse set of skills by interacting with an environment without any external supervision is an important challenge. In particular, obtaining a goal-conditioned agent that can reach any given state is useful i…
continuous-controlContinuous ControlExploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
Exploration remains the key bottleneck for large language model agents trained with reinforcement learning. While prior methods exploit pretrained knowledge, they fail in environments requiring the discovery of novel sta…
Reinforcement LearningDrugSAGE:Self-evolving Agent Experience for Efficient State-of-the-Art Drug Discovery
Building state-of-the-art (SOTA) predictive models for drug discovery requires expensive search over tools, architectures, and training strategies. Current LLM-based agents can find SOTA solutions through extensive trial…
Molecular Property PredictionDrug DiscoveryUnified Mind Model: Reimagining Autonomous Agents in the LLM Era
Large language models (LLMs) have recently demonstrated remarkable capabilities across domains, tasks, and languages (e.g., ChatGPT and GPT-4), reviving the research of general autonomous agents with human-like cognitive…
Instruction FollowingAGI Maze as a Benchmark Framework for World-Modeling Agents
Large language models (LLMs) are powerful pattern-completion systems, but their default operating mode - predicting the next token from a static context - does not reliably produce persistent, manipulable representations…