SPEM: Structure-Aware Procedural Memory for Efficient Skill Use in LLM Agents

Ran Zhou; Zehui Kong; Fanyu Lin; Jiaheng Liu; Zhen Zhang; Yuxiang Ren

cs.AIOct 19, 2026

SPEM: Structure-Aware Procedural Memory for Efficient Skill Use in LLM Agents

Authors: Ran Zhou, Zehui Kong, Fanyu Lin, Jiaheng Liu, Zhen Zhang, Yuxiang Ren

Organizations: School of Intelligence Science and Technology, Nanjing University

Abstract

LLM-based agents increasingly rely on reusable skills. However, scaling skill libraries makes efficient and accurate skill use difficult. Full skill loading incurs high token and runtime overhead. In contrast, flat semantic retrieval treats skills as independent text entries, ignoring dependencies, execution order, state transitions, and data flow constraints. We propose SPEM, a lightweight structure-aware procedural memory framework for efficient skill use in LLM-based agents. SPEM maintains Atomic Skill Memory for individual skills and Skill-DAG Memory for reusable compositions derived from successful executions. For a new task, SPEM reuses high-confidence Skill-DAG templates when available. Otherwise, it retrieves atomic skills and invokes Skill-GNN for state- and structure-aware skill selection. Successful executions are written back as new Skill-DAGs, allowing procedural memory to accumulate over time. Experiments on ALFWorld and SkillsBench show that SPEM achieves the best overall effectiveness--efficiency trade-off, reaching 87.1% ALFWorld success and 38.38% SkillsBench reward while reducing token and runtime costs against strong baselines.

Figures & tables

Figure 1: Overview of SPEM . The system retrieves atomic skills or matched Skill-DAG templates from dual-layer procedural memory, constructs a task-conditioned candidate skill graph, and uses Skill-GNN to produce compact guidance for the LLM executor. Successful trajectories are distilled back into reusable Skill-DAG memory.

Figure 2: Overview of trajectory-DAG extraction. Successful trajectories are converted into execution graphs, from which necessary steps are identified through backward slicing, pruning, and dependency repair. The resulting backbones are stored as reusable Skill-DAG templates for future tasks.

Backbone	Method	SkillsBench			ALFWorld
Backbone	Method	R $\uparrow$	T $\downarrow$	S $\downarrow$	Success $\uparrow$	Steps $\downarrow$	Tokens $\downarrow$	Runtime $\downarrow$
MiniMax-M2.7	Vanilla Skills	21.61	798,323	469.3	59.3	21.24	152,242.1	55.95s
	Vector Skills	13.07	722,765	439.5	63.9	18.36	55,816.6	55.71s
	GoS	23.50	735,113	399.4	68.6	20.26	62,033.9	54.22s
	SkillDAG	27.09	979,781	476.1	63.3	16.37	296,512.4	137.38s
	Ours	25.14	721,926	360.5	70.7	18.29	45,785.7	51.56s

Table 1: Main results on SkillsBench and ALFWorld under different backbone models. For SkillsBench, R denotes the verifier reward, T denotes average input tokens, and S denotes agent-only runtime in seconds. For ALFWorld, Success denotes task success rate, while Steps, Tokens, and Runtime denote average environment steps, average token consumption, and agent-only runtime, respectively.

\uparrow

indicates higher is better, and

\downarrow

indicates lower is better. Bold numbers indicate the best result within each backbone group and benchmark, and underlined numbers indicate the second-best result.

Figure 3: Effectiveness and scalability analysis. (a) Trajectory-DAG extraction compresses successful trajectories into compact DAG backbones. (b) Exact-DAG template reuse reduces normalized execution cost. (c) Hit@K under different skill library sizes. (d) Recall@K and MRR under different skill library sizes. Solid lines denote GNN-based reranking, while dashed lines denote retrieval-only selection.

Backbone	Hit	Fallback	Ineffective	Hit Success
MiniMax-M2.7	56.43	43.57	25.32	74.68
GPT-5.2-Codex	60.71	39.29	14.12	85.88

Table 2: Template-availability analysis on ALFWorld. All values are percentages.

Method Variant	Succ. $\uparrow$	Steps $\downarrow$	Time $\downarrow$	Tokens $\downarrow$
w/o Skill-DAG	56.8	23.0	55.4	67.5K
w/o Skill-GNN †	58.3	20.3	54.7	53.6K
w/o DAG Extraction	63.0	18.9	57.8	56.2K
Full SPEM	70.7	18.3	51.6	45.8K

Table 3: Component ablation of SPEM on ALFWorld. Succ., Steps, Time, and Tokens denote task success rate, average completion steps, average runtime, and average token consumption. † removes graph-based Skill-GNN and uses retrieved procedural memory.

Procedural Memory for LLM Agents

See all 10 papers

HyperSkill: Self-Evolving LLM Agents via Hypergraph-Structured Skill Memory
Aug 17, 2026Ruiyao Xu, Tiankai Yang, Wei-Chieh HuangAgent Memory LLM Agent Memory
Northwestern University · University of Southern California · University of Illinois at Chicago
LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents
Jun 4, 2026Aofan Yu, Chenyu Zhou, Tianyi Xu +8LLM Agent Skill Learning In-Context Learning
Shanghai Jiao Tong University · Sun Yat-Sen University · Shanghai Innovation Institute +1
When Not to Imitate: Boundary-Aware Skill Memory for Reliable Tool-Use LLM Agents
Aug 23, 2026Zihan Lin, Zhenyu Chen, Jiawen Wei +6LLM Agent Memory LLM Agent Skill Learning
Meituan · School of Advanced Interdisciplinary Sciences, University of Chinese Academy of Sciences · MAIS&NLPR, Institute of Automation, Chinese Academy of Sciences +1

Aug 17, 2026J/K move · Enter open · S save

HyperSkill: Self-Evolving LLM Agents via Hypergraph-Structured Skill Memory

Ruiyao Xu, Tiankai Yang, Wei-Chieh Huang

Northwestern University · University of Southern California · University of Illinois at Chicago

Agent Memory LLM Agent Memory Agent Memory Management LLM Agent Skill Retrieval Graph-Based Agent Memory

Open paper AskPDF arXiv

As agentic tasks grow in complexity, LLM agents increasingly rely on experiential memory to reuse procedural knowledge across tasks. Effective memory design must jointly address what to store, how memory is structured and retrieved, and how memory evolves. Existing systems tackle each only partially: they store trajectories, insights, or workflows as isolated entries, discarding compositional relationships among subtasks and reusable skills; retrieve by flat embedding similarity that ignores relational signals; and maintain memory without leveraging its relational structure. We propose HyperSkill, a hypergraph-based memory framework that jointly improves all three. HyperSkill represents memory as a hypergraph with two node types, subtask steps and reusable skills, where each hyperedge links the subtasks and skills from a single trajectory. Dual-path retrieval queries both subtask and trajectory levels, ranking skills by co-occurrence across retrieved trajectories. Periodic structure-informed maintenance prunes low-utility nodes and merges redundant skills via quality-weighted propagation. Across xBench, GAIA, and WebWalkerQA with GPT-4o and Qwen3-30B-A3B, HyperSkill outperforms ten memory baselines, yielding gains of up to +11.51 on GAIA and +11.18 on WebWalkerQA.

Abstract

Procedural Memory for LLM Agents

Explore similar work

HyperSkill: Self-Evolving LLM Agents via Hypergraph-Structured Skill Memory

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents

When Not to Imitate: Boundary-Aware Skill Memory for Reliable Tool-Use LLM Agents