ExpeL
LLM agents are experiential learners. AAAI 2024.
At a glance
- Type
- LLM agents as experiential learners
- Tier
- T3
- Created
- 2023-08-20 (arxiv 2308.10144 submitted August 20 2023; AAAI 2024)
- 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
- episode
- governance
- inspectable
- conflict
- llm-arbitrate
When to use
Optimised for: not applicable - research paper
Anti-fit: not applicable - research paper
Pros & cons
Pros
Defines LLM agents as experiential learners — explicit experience-extraction across tasks; AAAI 2024.
Cons
Extraction quality bounded by base model; experience storage scales with task count.
Claims & capabilities
LLM agent extracts knowledge as natural language from training tasks without parameter updates; in-context learning over accumulated experiences; AAAI 2024. Headline: 59% success on ALFWorld, beating ReAct (40%) and matching/exceeding Reflexion without task reattempts; baselines: ReAct and Act agents; primary datasets: HotpotQA (100 val), ALFWorld (134 solvable), WebShop (100), FEVER.
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.
Related systems
References (1)
- Reflexion cites — S2 isInfluential citation
Referenced by (4)
- G-Memory cites — S2 isInfluential citation
- H²R cites — S2 isInfluential citation
- MemEvolve cites — S2 isInfluential citation
- MIA — Memory Intelligence Agent cites — S2 isInfluential citation