ActionRAG: Evidence-Refining Graph Diffusion for Long-Term Memory in LLM Agents

Navyansh Mahla; Sashank Vandrangi

cs.AIOct 23, 2026

ActionRAG: Evidence-Refining Graph Diffusion for Long-Term Memory in LLM Agents

Authors: Navyansh Mahla, Sashank Vandrangi

Organizations: Actioneer, Mountain View, California, USA

Abstract

LLM agents need long-term memory that can recover precise and mutually consistent evidence from growing interaction histories, particularly when answers depend on relations among facts rather than isolated semantic matches. Current memory pipelines remain vulnerable at two stages: indexing errors can fragment repeated entities or merge distinct ones, and online retrieval often treats initial similarity scores as final even when the surrounding graph provides evidence for revising them. We introduce ActionRAG, a graph memory architecture that couples cautious indexing with query-time graph retroevaluation. Its indexing pipeline reconciles type labels and applies tiered entity resolution. Given a query, dual-channel entity and triple retrieval forms an initial evidence set and induces a bounded local graph. Query-conditioned receiver-normalized diffusion refines triple scores using local path structure. Seed protection, hub-penalized flux, and triple materialization preserve direct evidence while recovering missed connections. We evaluate ActionRAG on MemoryAgentBench (MAB), which tests accurate retrieval, conflict resolution, long-range understanding, and test-time learning. Across its eight deterministic-scoring columns, ActionRAG achieves 55.1 average accuracy, improving over the strongest retrieval-based memory baseline by 5.4 points. Under MAB's query-time cost accounting, mean synthesis cost stays below $0.001 per query on the four reported cost columns, and the sum of separately measured retrieval-side p99 components is 440.7 ms on our consumer Apple Silicon setup.

Figures & tables

Panel of Figure 1 — Figure 1: ActionRAG online retrieval. A query retrieves entity nodes as expansion anchors and concrete triple edges as evidence items, then expands a bounded local evidence graph. Receiver-normalized diffusion scores the item set of concrete triples plus orphan entities; high raw-score items are protected, low-scoring evidence is pruned, and high-flux missing triples are materialized before the surviving facts are packed into the LLM context. Edge width denotes the diffused triple score.

Long-context agents
	AR			TTL		LRU	CR		Overall
Agent type	SH	MH	Event	MCC	Recom	DetQA	FC-SH	FC-MH	Avg.
GPT-4o-mini (128K)	64.0	43.0	59.0	82.0	15.1	63.4	45.0	5.0	47.1
GPT-4.1-mini (1M)	83.0	66.0	82.6	75.6	16.7	56.3	36.0	5.0	52.7
Simple RAG agents
BM25	66.0	56.0	74.6	75.4	13.6	52.1	48.0	3.0	48.6

Table 1: Deterministic scores on the selected MAB columns. Baseline numbers are from MAB Table 3. Unless a model is named in the agent row, MAB uses gpt-4o-mini as the answer generator. Avg. is the unweighted mean of the eight heterogeneous displayed scores . Bold marks the global column best and underline marks the best among structure-augmented RAG and agentic memory agents.

Graph construction	Recon.	Summ.	Base	PPR	ActionRAG
Raw exact-match triplet graph	string only	none	43.0	45.4	45.5
Summarized exact-match graph	string only	node/rel.	43.8	46.0	48.9
Reconciled ActionRAG graph	node/type/rel.	node/rel.+prov.	45.0	47.0	55.1

Table 2: Component attribution on MAB deterministic aggregate.

Agent	BANKING	CLINIC	NLU	TREC-C	TREC-F	Avg.
GPT-4o LC	96.0	96.0	90.0	87.0	69.0	87.6
Claude-3.7-Sonnet LC	97.0	98.0	86.0	87.0	79.0	89.4
GPT-4o-mini LC	93.0	93.0	87.0	73.0	66.0	82.4
Qwen3-Embedding-4B	90.0	88.0	86.0	67.0	59.0	78.0
MemoRAG	90.0	87.0	86.0	66.0	56.0	77.0
BM25	89.0	89.0	84.0	62.0	53.0	75.4

Table 3: MCC test-time learning accuracy and the baselines are from MAB Table 7.

Agent	MH-DocQA	MCC	DetQA	FC-SH
GPT-4o-mini LC	0.010 / 43.0	0.008 / 82.0	0.010 / 63.4	0.010 / 45.0
GPT-4.1-mini LC	0.043 / 66.0	0.011 / 75.6	0.013 / 56.3	0.027 / 36.0
BM25 + gpt-4o-mini	$<$ 0.001 / 56.0	0.006 / 75.4	0.006 / 52.1	$<$ 0.001 / 48.0
MIRIX (4.1-mini)	0.016 / 75.0	0.010 / 61.0	0.011 / 62.0	0.019 / 20.0
ActionRAG	0.00109 / 63.0	0.00031 / 82.0	0.00116 / 46.7	0.00111 / 61.3

Table 4: Per-query cost ($) / score on four MAB columns and the baselines are from MAB Table 17 under November 2025 prices.

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Dataset	Method	$k{=}2$	$k{=}5$	$k{=}10$
SH-DocQA	BM25	50.0	60.0	66.0
SH-DocQA	Text-Embed-3-Large	36.0	47.0	54.0
SH-DocQA	HippoRAG-v2	60.0	69.0	76.0
SH-DocQA	ActionRAG	76.0	76.0	77.0
MH-DocQA	BM25	49.0	54.0	56.0
MH-DocQA	Text-Embed-3-Large	37.0	41.0	44.0

Appendix

Table 5: Top-

k

accuracy:

k

is the chunk count for MAB baselines and

K_{E}{=}K_{T}{=}k

for ActionRAG seeds.

Config	BANK	CLINIC	NLU	TREC-C	TREC-F	MCC avg
default ( $\alpha=.15$ , $H=3$ , $\varepsilon=.1$ , $L=5$ , $S=10$ )	94.0	91.0	86.0	76.0	63.0	82.0
$\alpha=0.05$	94.0	90.0	85.0	82.0	63.0	82.8
$\alpha=0.50$	92.0	89.0	86.0	79.0	64.0	82.0
$\alpha=0.85$	95.0	89.0	86.0	86.0	68.0	84.8
$H=1$	93.0	88.0	87.0	83.0	63.0	82.8
$H=5$	92.0	89.0	87.0	80.0	66.0	82.8

Appendix

Table 6: One-at-a-time MCC sensitivity. Each row changes one default.

Embedder	Dim	BANK	CLINIC	NLU	TREC-C	TREC-F	MCC avg
BGE-M3	1024	94.0	89.0	86.0	84.0	67.0	84.0
text-embedding-3-large	3072	92.0	91.0	88.0	74.0	60.0	81.0
text-embedding-3-small	1536	90.0	92.0	87.0	78.0	51.0	79.6

Appendix

Table 7: MCC embedding sensitivity with fixed graph and retrieval settings.

Graph	Nodes	Tokens	Doc 1	Doc 2	Doc 3	Doc 4	Doc 5	Avg	$p_{50}$ ms	$p_{99}$ ms	Ctx tok	Items retr.
64K	409	$\sim$ 77.9K	72	77	73	74	70	73.2	2212	5811	6844	103
128K	775	$\sim$ 156.8K	69	75	69	69	70	70.4	2233	6325	6901	121
full	2948	$\sim$ 651K	75	76	63	67	64	69.0	2764	7664	6896	153
$\Delta$ 64K to full	7.2x	8.4x	+3	-1	-10	-7	-6	-4.2	+25%	+32%	$\sim$ flat	+1.5x

Appendix

Table 8: EventQA graph growth on matched 64K, 128K, and full questions.

Setting	Symbol	Value	Setting	Symbol	Value
entity seeds	$K_{E}$	10	hop cap	$H$	3
concrete triple seeds	$K_{T}$	10	distance decay	$\beta$	1.0
entity expansion depth	$D_{E}$	2	traversal floor	$\delta$	0.01
triple expansion depth	$D_{T}$	1	direct-evidence weight	$\alpha$	0.15
neighbors per expansion	n/a	8	prune threshold	$\varepsilon$	0.10
hub-degree cutoff	n/a	80	protected raw-score items	$S$	10

Appendix

Table 9: Fixed ActionRAG retrieval configuration.

LLM Agent Memory

Large language model agent memory lets agents retain, organize, retrieve, and update information across interactions and long-running tasks.

See all 373 papers

TAGGRAPH: Tag-Augmented Graphs for Graph Retrieval of Agent Persistent Histories
Sep 29, 2026Yu-Shu Chen, Yu-Jung Liang, Pengtao XieGraph-Based Retrieval Memory Agent Benchmarks
Department of Electrical and Computer Engineering University of California, San Diego La Jolla, CA 92093, USA
Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite
Aug 5, 2026Xiawei Yue, Boran Wang, Xiaoqing Zhang +2LLM Agent Memory Graph-Based Agent Memory
Nankai University, Tianjin, China · Zhongguancun Academy, Beijing, China · Beihang University, Beijing, China
RaMem: Contextual Reinstatement for Long-term Agentic Memory
Jun 22, 2026Wei Yang, Bryce Kan, Shixuan Li +5Agent Memory LLM Agent Memory
University of Southern California

Sep 29, 2026J/K move · Enter open · S save

TAGGRAPH: Tag-Augmented Graphs for Graph Retrieval of Agent Persistent Histories

Yu-Shu Chen, Yu-Jung Liang, Pengtao Xie

Department of Electrical and Computer Engineering University of California, San Diego La Jolla, CA 92093, USA

Graph-Based Retrieval Memory Agent Benchmarks Graph-Based Agent Memory Long-Term Conversational Memory

Open paper AskPDF arXiv

Long-term memory lets LLM agents recall past interactions and remain consistent across sessions, but memory systems are hard to compare because they often vary in representation, indexing, retrieval, and evaluation. We present a controlled evaluation framework based on shared 5W-style conversational memories. Localized graph configurations traverse a common base graph; AdaptiveGraph adds chronological edges and Personalized PageRank diffusion. We also evaluate BM25 over the same extracted notes and OpenClaw as a raw-input external reference. Retrieval rankings vary across memory settings. On LongMemEval-S, AdaptiveGraph is the strongest graph configuration at 0.844 MRR, but BM25 reaches 0.867 and OpenClaw 0.880. On ATANT Core, localized graph traversal outperforms diffusion and BM25, whereas BM25 leads the stress rounds. Reducing LongMemEval-S within the tested range does not reproduce the ATANT diffusion penalty, but the smallest tested store remains larger than ATANT Core, so store size cannot be ruled out. The penalty also persists under a permissive content-match criterion. Vocabulary normalization and extraction quality substantially affect graph retrieval, and missing extraction tags are common among top-five misses. Retrieval strategies should therefore be evaluated jointly with the memory setting and against strong lexical baselines.

Abstract

LLM Agent Memory

Explore similar work

TAGGRAPH: Tag-Augmented Graphs for Graph Retrieval of Agent Persistent Histories

Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite

RaMem: Contextual Reinstatement for Long-term Agentic Memory