mlsanityData to 14 Oct 2026

Toward Efficient Agents: Memory, Tool learning, and Planning

arXiv 2601.14192 ↗First posted 20 Jan 2026cs.AI cs.CLcited by 16

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Recent years have witnessed increasing interest in extending large language models into agentic systems. While the effectiveness of agents has continued to improve, efficiency, which is crucial for real-world deployment, has often been overlooked. This paper therefore investigates efficiency from three core components of agents: memory, tool learning, and planning, considering costs such as latency, tokens, steps, etc. Aimed at conducting comprehensive research addressing the efficiency of the agentic system itself, we review a broad range of recent approaches that differ in implementation yet frequently converge on shared high-level principles including but not limited to bounding context via compression and management, designing reinforcement learning rewards to minimize tool invocation, and employing controlled search mechanisms to enhance efficiency, which we discuss in detail. Accordingly, we characterize efficiency in two complementary ways: comparing effectiveness under a fixed cost budget, and comparing cost at a comparable level of effectiveness. This trade-off can also be viewed through the Pareto frontier between effectiveness and cost. From this perspective, we also examine efficiency oriented benchmarks by summarizing evaluation protocols for these components and consolidating commonly reported efficiency metrics from both benchmark and methodological studies. Moreover, we discuss the key challenges and future directions, with the goal of providing promising insights.

Key facts. Cited by 16 papers in the map (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 143 of its 244 references that are in the map. First posted on arXiv 20 Jan 2026.

Builds on

143 of 244 references.

Closest ancestors · 33

Same direction, newest first

  1. 2026Beyond Entangled Planning: Task-Decoupled Planning for Long-Horizon Agents12 Jan
  2. 2025Benchmark for Planning and Control with Large Language Model Agents: Blocksworld with Model Context Protocol3 Dec
  3. 2025Latent Collaboration in Multi-Agent Systems25 Nov
  4. 2025Budget-Aware Tool Use Enables Effective Agent Scaling21 Nov
  5. 2025CostBench: Evaluating Multi-Turn Cost-Optimal Planning and Adaptation in Dynamic Environments for LLM Tool-Use Agents4 Nov
  6. 2025TPS-Bench: Evaluating AI Agents' Tool Planning & Scheduling Abilities in Compounding Tasks3 Nov
  7. 2025Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems30 Oct
  8. 2025GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learning29 Oct
  9. 2025A2FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning13 Oct
  10. 2025A Survey on Agentic Multimodal Large Language Models13 Oct
  11. 2025MARS: toward more efficient multi-agent collaboration for LLM reasoning24 Sep
  12. 2025Learning When to Plan: Efficiently Allocating Test-Time Compute for LLM Agents3 Sep
21 more
  1. 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios25 Aug
  2. 2025SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication15 Aug
  3. 2025RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent LLM Systems with Structured Memory6 Aug
  4. 2025Efficient Agents: Building Effective Agents While Reducing Cost24 Jul
  5. 2025CodeAgents: A Token-Efficient Framework for Codified Multi-Agent Reasoning in LLMs4 Jul
  6. 2025Alita: Generalist Agent Enabling Scalable Agentic Reasoning with Minimal Predefinition and Maximal Self-Evolution26 May
  7. 2025Distilling LLM Agent into Small Models with Retrieval and Code Tools23 May
  8. 2025AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems1 Apr
  9. 2025ReSo: A Reward-driven Self-organizing LLM-based Multi-Agent System for Reasoning Tasks4 Mar
  10. 2025LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning8 Feb
  11. 2024BudgetMLAgent: A Cost-Effective LLM Multi-Agent system for Automating Machine Learning Tasks12 Nov
  12. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systems3 Oct
  13. 2024Sibyl: Simple yet Effective Agent Framework for Complex Real-world Reasoning15 Jul
  14. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains17 Jun
  15. 2024Scaling Large Language Model-based Multi-Agent Collaboration11 Jun
  16. 2024Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models19 Mar
  17. 2024Understanding the planning of LLM agents: A survey5 Feb
  18. 2024MAGDi: Structured Distillation of Multi-Agent Interaction Graphs Improves Reasoning in Smaller Language Models2 Feb
  19. 2023Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models6 Oct
  20. 2023TPTU: Large Language Model-based AI Agents for Task Planning and Tool Usage7 Aug
  21. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks27 May

Other references · 110

  1. 2024GPT-4o System Cardcited by 4,588
  2. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  3. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 2,006
  4. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  5. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  6. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  7. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 867
  8. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 779
  9. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 707
  10. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 647
  11. 2025τ2-Bench: Evaluating Conversational Agents in a Dual-Control Environmentcited by 627
  12. 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Searchcited by 422
38 more
  1. 2025Accelerating scientific discovery with Co-Scientistcited by 401
  2. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memorycited by 400
  3. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Modelscited by 398
  4. 2025ReTool: Reinforcement Learning for Strategic Tool Use in LLMscited by 392
  5. 2024Measuring short-form factuality in large language modelscited by 373
  6. 2025ToolRL: Reward is All Tool Learning Needscited by 362
  7. 2024Titans: Learning to Memorize at Test Timecited by 328
  8. 2025Memory in the Age of AI Agentscited by 303
  9. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 284
  10. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 256
  11. 2025MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agentcited by 246
  12. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agentscited by 238
  13. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learningcited by 237
  14. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Usecited by 217
  15. 2024A Survey on Efficient Inference for Large Language Modelscited by 205
  16. 2023Efficient Large Language Models: A Surveycited by 186
  17. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 184
  18. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  19. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 180
  20. 2025MIRIX: Multi-Agent Memory System for LLM-Based Agentscited by 173
  21. 2025Dynamic Cheatsheet: Test-Time Learning with Adaptive Memorycited by 163
  22. 2026SimpleMem: Efficient Lifelong Memory for LLM Agentscited by 149
  23. 2025MemOS: A Memory OS for AI Systemcited by 138
  24. 2025Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memorycited by 136
  25. 2024StableToolBench: Towards Stable Large-Scale Benchmarking on Tool Learning of Large Language Modelscited by 132
  26. 2025A Survey of Efficient Reasoning for Large Reasoning Models: Language, Multimodality, and Beyondcited by 132
  27. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMscited by 127
  28. 2024MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentationcited by 119
  29. 2025SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMscited by 116
  30. 2025Agentic Reasoning and Tool Integration for LLMs via Reinforcement Learningcited by 110
  31. 2025MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Serverscited by 109
  32. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agentscited by 109
  33. 2023ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Searchcited by 105
  34. 2024Long Context Compression with Activation Beaconcited by 104
  35. 2025AgentFold: Long-Horizon Web Agents with Proactive Context Managementcited by 103
  36. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agentscited by 102
  37. 2023MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversationcited by 97
  38. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 94

50 most cited of 110 All 110 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 16.

16 papers.

Sort:

By area:

  1. 2026Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitationscited by 21
  2. 2026LLM Agents Already Know When to Call Tools -- Even Without Reasoningcited by 19
  3. 2026LatentMem: Customizing Latent Memory for Multi-Agent Systemscited by 15
  4. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  5. 2026Safety in Embodied AI: A Survey of Risks, Attacks, and Defensescited by 7
  6. 2026HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolutioncited by 6
  7. 2026From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AIcited by 6
  8. 2026Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agentscited by 5
  9. 2026Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testingcited by 4
  10. 2026Prompt-Induced Waste in Coding Agents: Reasoning, Effort, Harness Design, and End-to-End Costcited by 1
  11. 2026MobileMem: Learning from a Year of Mobile Experiencescited by 1
  12. 2026READER: Dynamic LLM Provenance from Query-Varying Interactionscited by 0
4 more
  1. 2026Tool-Adaptive LLM Rerankercited by 0
  2. 2026Piggybacking on Perception: Stealthy Concurrent Audio Prompt Injections against Multimodal LLM Agentscited by 0
  3. 2026OpenClaw and Ollama in Agentic AI: Toward Fully Autonomous and Scalable AI Agent Systemscited by 0
  4. 2026Efficient GUI Agents: A Systems Survey of Observation, Memory, Action, and Runtime Optimizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026On Effectiveness and Efficiency of Agentic Tool-calling and RL Training
  2. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
  3. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
  4. 2026EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
  5. 2026Scaling Agentic Capabilities, Not Context: Efficient Reinforcement Finetuning for Large Toolspaces
  6. 2026Rethinking the Evaluation of Efficiency Methods for Multi-Agent Systems
  7. 2026EASy: Towards Efficient LLM-Based Agentic System
  8. 2026Tool-Aware Optimization with Entropy Guidance for Efficient Agentic Reinforcement Learning