BytedTsinghua-SIA/MemAgent

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1100 stars · 73 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

MemAgent is a reinforcement-learning framework for training LLM agents that process arbitrarily long contexts via a memory mechanism within fixed context windows. It extends the DAPO algorithm to support end-to-end RL optimization of multi-turn agent workflows, enabling extrapolation from 32K training contexts to 3.5M-token tasks.

Use cases

• train an LLM agent to handle multi-million-token documents
• do RL training on multi-turn agent workflows with verifiable rewards
• extend a model's effective context length beyond its training window
• run long-context QA with linear compute scaling
• reproduce RL-MemAgent-7B/14B long-context results

When to choose

• you need RL training of agent workflows with long-context memory
• you want to extrapolate context length without changing model architecture
• you need linear-time long-text processing

When to avoid

• you only need inference-time RAG without training
• you lack GPU resources for RL fine-tuning
• you need a plug-and-play long-context model with no training

Facets

framework · maturity active

llm-training agent-framework rag machine-learning large-language-models artificial-intelligence deep-learning python reinforcement-learning long-context memory-agent rlvr dapo context-extrapolation ai-agents gpu linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="BytedTsinghua-SIA/MemAgent")