Back to Arena
KnowAgent
by zjunlp (Zhejiang University)
System Card
Organizationzjunlp (Zhejiang University)
Released2024-03
Architectureknowledge-base / Action-knowledge base + self-learning
DetailsBuilds an "action knowledge base" converted to text for the LLM; uses knowledgeable self-learning (LoRA fine-tune on iterative trajectories) to refine plans. Works with Llama 7B/13B/70B on HotpotQA/ALFWorld.
Parameters—
Domainagent-memoryknowledge-graphlifelong-learning
Open SourceYes
PaperView Paper
CodeRepository
action-kbnaacl-2025self-learningpaper-repo
Capability Profile
Benchmark Scores
6 of 14 benchmarksLong-Context Retrieval0/5
RULER
no dataNIAH
no dataLooGLE
no dataLongBench
no data∞Bench
no dataMulti-Turn Recall1/2
MemoryBank
no dataCross-Session Memory1/1
Multi-Hop QA3/3
Agent Task Memory1/1
Personalization0/1
PerLTQA
no dataFactuality / Grounding0/1
RAGAS
no dataSources:arXiv:2403.03101 Table 1 — KnowAgent-70b (Llama-2-70b-chat) F1 averaged across Easy/Medium/HardKnowAgent paper (arXiv:2403.03101); evaluated on LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory (Salesforce AI Research, 2410)KnowAgent paper (arXiv:2403.03101); evaluated on LoCoMo: Long-Term Conversational Memory Benchmark (Snap Research, 2402)KnowAgent paper (arXiv:2403.03101); evaluated on MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries (HKUST, 2401)KnowAgent paper (arXiv:2403.03101); evaluated on AgentBench Memory Track (Tsinghua KEG, 2308)KnowAgent paper (arXiv:2403.03101); evaluated on BABILong: Testing the Limits of LLMs with Long-Context Reasoning-in-a-Haystack (AIRI, 2406)