Pith. sign in

REVIEW 8 cited by

AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.04363 v3 pith:5P2LTQZT submitted 2024-07-05 cs.AI

classification cs.AI
keywords memoryagentsarigraphknowledgeagentcomplexdecision-makingenvironments
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Advancements in the capabilities of Large Language Models (LLMs) have created a promising foundation for developing autonomous agents. With the right tools, these agents could learn to solve tasks in new environments by accumulating and updating their knowledge. Current LLM-based agents process past experiences using a full history of observations, summarization, retrieval augmentation. However, these unstructured memory representations do not facilitate the reasoning and planning essential for complex decision-making. In our study, we introduce AriGraph, a novel method wherein the agent constructs and updates a memory graph that integrates semantic and episodic memories while exploring the environment. We demonstrate that our Ariadne LLM agent, consisting of the proposed memory architecture augmented with planning and decision-making, effectively handles complex tasks within interactive text game environments difficult even for human players. Results show that our approach markedly outperforms other established memory methods and strong RL baselines in a range of problems of varying complexity. Additionally, AriGraph demonstrates competitive performance compared to dedicated knowledge graph-based methods in static multi-hop question-answering.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Experience-Evolving Multi-Turn Tool-Use Agent with Hybrid Episodic-Procedural Memory

    cs.LG 2025-12 conditional novelty 6.0 of 10

    An LLM agent that builds a tool-transition graph with state summaries from past experience improves tool selection and RL exploration by large margins on multi-turn benchmarks.

  2. The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems

    cs.IR 2025-07 conditional novelty 6.0 of 10

    A framework for agentic recommender systems plus a pilot study showing multi-agent pipelines beat a single-shot LLM only on high-diversity user histories.

  3. A Taxonomy of Cognitive Capability Gaps in Generative and Agentic AI

    cs.AI 2026-08 conditional novelty 5.0 of 10

    The paper organizes persistent AI limitations into a five-part taxonomy of cognitive capability gaps and proposes a conceptual ACIA architecture and cognition-centric metrics, none of which are validated.

  4. KnowMap: Efficient Knowledge-Driven Task Adaptation for LLMs

    cs.CL 2025-06 conditional novelty 5.0 of 10

    Fine-tuning a 0.56B-parameter embedding model to retrieve environment and experience knowledge improves gpt-4-turbo's ScienceWorld task score from 64.78 to 76.25.

  5. Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities

    cs.AI 2025-06 conditional novelty 5.0 of 10

    A survey that groups graph-empowered AI agent research into planning, execution, memory, and multi-agent coordination, plus agents-for-graphs and applications.

  6. Cognitive Weave: Synthesizing Abstracted Knowledge with a Spatio-Temporal Resonance Graph

    cs.AI 2025-06 conditional novelty 4.0 of 10

    Cognitive Weave is a memory framework for LLM agents that combines vector, temporal, and relational storage with LLM-generated insight summaries, reporting gains in planning, evolving QA, and dialogue coherence.

  7. Toward Efficient Agents: Memory, Tool learning, and Planning

    cs.AI 2026-01 conditional novelty 3.0 of 10

    A survey that organizes efficiency techniques for LLM agents into memory, tool learning, and planning, and consolidates benchmarks and metrics for measuring cost-performance trade-offs.

  8. Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects

    cs.AI 2025-07 conditional novelty 3.0 of 10

    A survey that categorizes Graph-augmented LLM Agent research into planning, memory, tool management, and multi-agent design, and outlines open directions.

Pith tools