When Should Agents Check External State? Budgeting Observations for Stored Intentions
cs.AI
Submitted: 2026-09-29
Updated: 2026-09-30
Sources
- FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
- Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- The Llama 3 Herd of Models
- MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks
- Learning What to Remember: Observability-Safe Memory Retention via Constrained Optimization for Long-Horizon Language Agents
- MDPs with a State Sensing Cost
- MemoryCPT: An End-to-End Agent Memory Framework for Cost-Performance Trade-off
- WISERouter: LLM Routing with Workload Budget Constraint
- LeanMem: Simple and Efficient Long-Term Memory for LLM Agents
- Budget-Constrained Agentic Large Language Models: Intention-Based Planning for Costly Tool Use
- Budget-Aware Tool-Use Enables Effective Agent Scaling
- MemGPT: Towards LLMs as Operating Systems
- Qwen2.5 Technical Report
- Policy Distillation
- LLM Agents Already Know When to Call Tools -- Even Without Reasoning
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
- Remember When It Matters: Proactive Memory Agent for Long-Horizon Agents
- Qwen3 Technical Report
- Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory
- TriggerBench: Investigating Prospective Memory for Large Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems