MPO

Boosts LLM agents with meta plan optimisation. EMNLP 2025.

At a glance

Type
Meta plan optimisation
Tier
T3
Created
2025-03 (MPO: Boosting LLM Agents with Meta Plan Optimization; arxiv 2503.02682 submitted March 2025)
Latest release
not applicable — not OSS
License
not applicable — not OSS
GitHub
not applicable — no GitHub repo
Pricing
not applicable — not commercial
Funding
not applicable — not commercial

Taxonomy

storage
vector
retrieval
similarity
persistence
cross-session
update
extraction
unit
skill
governance
n/a
conflict
llm-arbitrate

When to use

Optimised for: not applicable - research paper

Anti-fit: not applicable - research paper

Pros & cons

Pros

Boosts LLM agents with meta plan optimisation — explicit plan-level improvement loop; EMNLP 2025.

Cons

Plan-optimization adds inference cost; quality bounded by base planner.

Claims & capabilities

Meta Plan Optimization framework that incorporates explicit guidance via high-level meta plans, continuously optimized from task execution feedback; plug-and-play solution avoiding retraining for new agents; significantly outperforms baselines on two representative tasks; EMNLP 2025 Findings

Technical surface

API surface
not applicable — research paper
Backend storage
not applicable — research paper
Deployment
not applicable — not a deployable product
Embedding model
not applicable — research paper
Multi-tenancy
not applicable — research paper
MCP
not applicable — research paper, no deployed product
A2A
not applicable — research paper, no deployed product
OpenTelemetry
not applicable — research paper, no deployed product

Similar systems

Other recent method papers — theorized, no distinct product in the catalog, ranked by inbound references.

  • Compressive Transformer T3

    Maintains recent states in full resolution while compressing older memories with learned compression functions. DeepMind.

  • MemGPT v2 / agent-tools T3

    Already in catalog as the foundational MemGPT paper. Note: Letta is the productionised successor (cross-listed).

  • Transformer-XL T3

    Extends context through segment-level recurrence + caching of hidden states from prior segments. Foundational long-context architecture.

  • Generative Agents T3

    Park et al. — landmark agent-simulation paper. Reflection + memory stream + retrieval enable believable agent behavior.

  • MemoryBank T3

    Enhances LLMs with long-term memory. Early influential paper.

  • Reflexion T3

    Language agents with verbal reinforcement learning.

Row last verified 2026-05-14. Catalog data is CC-BY-4.0 — see how to read this.