# When Should Agents Check External State? Budgeting Observations for Stored Intentions

arXiv: https://arxiv.org/abs/2609.37125 · HTML: https://mlsanity.com/paper/2609.37125/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 33 of its 40 references that are in the map.
- First posted on arXiv 29 Sep 2026.

## Builds on (most cited first, 30 of 33)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance](https://mlsanity.com/paper/2305.05176/) (2023)
- [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)
- [RouteLLM: Learning to Route LLMs with Preference Data](https://mlsanity.com/paper/2406.18665/) (2024)
- [Policy Distillation](https://mlsanity.com/paper/1511.06295/) (2015)
- [Bandits with Knapsacks](https://mlsanity.com/paper/1305.2545/) (2013)
- [MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks](https://mlsanity.com/paper/2602.16313/) (2026)
- [Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agents](https://mlsanity.com/paper/2601.01885/) (2026)
- [Budget-Aware Tool Use Enables Effective Agent Scaling](https://mlsanity.com/paper/2511.17006/) (2025)
- [CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents](https://mlsanity.com/paper/2511.02734/) (2025)
- [Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models](https://mlsanity.com/paper/2409.20222/) (2024)
- [LLM Agents Already Know When to Call Tools -- Even Without Reasoning](https://mlsanity.com/paper/2605.09252/) (2026)
- [Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory](https://mlsanity.com/paper/2602.06025/) (2026)
- [Lightweight LLM Agent Memory with Small Language Models](https://mlsanity.com/paper/2604.07798/) (2026)
- [Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents](https://mlsanity.com/paper/2607.08716/) (2026)
- [Towards Painless Policy Optimization for Constrained MDPs](https://mlsanity.com/paper/2204.05176/) (2022)
- [Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use](https://mlsanity.com/paper/2602.11541/) (2026)
- [Optimal Value of Information in Graphical Models](https://mlsanity.com/paper/1401.3474/) (2014)
- [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)
- [Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents](https://mlsanity.com/paper/2606.10616/) (2026)
- [LeanMem: Simple and Efficient Long-Term Memory for LLM Agents](https://mlsanity.com/paper/2608.03463/) (2026)
- [WISERouter: LLM Routing with Workload Budget Constraint](https://mlsanity.com/paper/2607.23765/) (2026)

## Abstract (arXiv)

Prospective memory allows an agent to retain an intention tied to a future condition, but the stored intention does not reveal whether that condition currently holds. Checking it may require web access, multi-step tool use, and paid calls. Existing systems decide when intentions require attention, but do not allocate the resulting observations under a shared budget. We introduce the first resource-allocation formulation for the external observations required by stored intentions under a shared episode budget. BudgetPM offers two policy variants that share a hard-budget executor. BudgetPM-Static uses a lightweight Logistic scorer to learn whether a check improves the current decision. BudgetPM-Sequential distills full-episode hindsight schedules into a lightweight policy that decides when to spend or reserve capacity using only pre-query information at deployment. We evaluate BudgetPM against two public memory-agent systems, five matched controls, and four hand-designed monitoring or budget-adaptation rules. Across two benchmarks and three backbones, BudgetPM-Static outperforms adapted Mem0 and PMA workflows. On PM-Bench, its Logistic scorer reaches competitive quality--cost operating points alongside higher-capacity scorers and retains 99.9--100% of unconstrained quality with 42--54% fewer observations. Under severe scarcity and the same hard caps, BudgetPM-Sequential exceeds the strongest tested natural monitoring schedule by 1.92--2.58 Set F1 points. It reaches the same Set F1 and on-time recall with 16--33% fewer observations. Matched attribution, exact-cost analysis, and a fixed-budget load intervention link this gain to competition between present and future opportunities. These results yield a demand--capacity design rule: local gating works when capacity covers demand, while future-aware supervision adds value when observations compete across time.