# Making Prospective Memory SLM-Shaped: Typed Intention Stores for Small-Model Agents

arXiv: https://arxiv.org/abs/2609.01272 · HTML: https://mlsanity.com/paper/2609.01272/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 25 references that are in the map.
- First posted on arXiv 1 Sep 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 19 of 19)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Gemma 2: Improving Open Language Models at a Practical Size](https://mlsanity.com/paper/2408.00118/) (2024)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [LightMem: Lightweight and Efficient Memory-Augmented Generation](https://mlsanity.com/paper/2510.18866/) (2025)
- [Memory OS of AI Agent](https://mlsanity.com/paper/2506.06326/) (2025)
- [TinyAgent: Function Calling at the Edge](https://mlsanity.com/paper/2409.00608/) (2024)
- [Octopus v2: On-device language model for super agent](https://mlsanity.com/paper/2404.01744/) (2024)
- [Lightweight LLM Agent Memory with Small Language Models](https://mlsanity.com/paper/2604.07798/) (2026)
- [Small Language Models for Agentic Systems: A Survey of Architectures, Capabilities, and Deployment Trade offs](https://mlsanity.com/paper/2510.03847/) (2025)
- [PM-Bench: Evaluating Prospective Memory in LLM Agents](https://mlsanity.com/paper/2607.12385/) (2026)
- [TriggerBench: Investigating Prospective Memory for Large Language Models](https://mlsanity.com/paper/2606.23459/) (2026)
- [DuoMem: Towards Capable On-Device Memory Agents via Dual-Space Distillation](https://mlsanity.com/paper/2606.29961/) (2026)

## Built on by (most cited first, 1 of 1)

- [When Should Agents Check External State? Budgeting Observations for Stored Intentions](https://mlsanity.com/paper/2609.37125/) (2026)

## Abstract (arXiv)

Prospective memory means carrying out a deferred intention at the right future cue while other work continues. Benchmarks now isolate it as an agent skill, yet frontier LLMs still struggle: the best published PM-Bench scaffold reaches only 65.1% Set-F1. We argue that this loop is schema-constrained state tracking rather than open-ended reasoning, and that small models can execute it when the action space is typed. We propose the Prospective Intention Store (PIS) that puts lifecycle logic in code and scoped language work on the model. The scaffold is agentic and training-free: no selector fine-tuning and no trajectory distillation. On PM-Bench, DeepSeek-Chat with PIS reaches 82.9% Set-F1. On Gemma-E2B, Set-F1 is only 4.2% without a store and at most 6.6% under seven retrospective memories, while PIS reaches 66.2%. PIS further reaches 70.1% Set-F1, where retrospective memory methods stay at most 54.4%. PIS sets a new state of the art on this benchmark and enables small models to surpass the published large-model scaffold.