mlsanityData to 14 Oct 2026

ToolAtlas: Learning Once, Reusing Everywhere with Tool-Side Memory

arXiv 2607.11126 ↗First posted 13 Jul 2026cs.LGcited by 0

On the map: LLM agents and tool use → Tool learning and function calling

Abstract (arXiv)

Large language model (LLM) agents increasingly rely on external tools served by shared providers and accessed by heterogeneous downstream agents. Existing approaches improve tool use on the agent side through parameter updates, prompt refinement, or agent-side memory, making tool knowledge difficult to share and limited to behaviors observed in past tasks. We argue that reusable tool knowledge should instead be maintained by the tool provider. We introduce ToolAtlas, a graph-based framework that builds a persistent provider-side tool memory of tool capabilities, failure boundaries, and cross-tool compositions through execution-verified probing. At inference time, agents query the tool memory via adaptive graph traversal. Across two MCP-based benchmarks spanning eight services, ToolAtlas outperforms existing tool-side optimization and agent-side memory baselines by up to 21.61% in pass@1 and 18.61% in pass@4. The same tool memory also transfers across environment instances and agent frameworks without retraining or task-time exploration, yielding up to 24.16%/16.22% and 17.49%/14.27% relative gains in pass@1/pass@4, respectively. Ablation studies show that these gains arise from combining tool-centered memory organization with capability-guided execution probing. These results establish provider-side tool memory as an effective and reusable paradigm for tool servers. Our code is in: https://github.com/PuppyKnightUniversity/ToolAtlas.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 19 of its 33 references that are in the map. First posted on arXiv 13 Jul 2026.

Builds on

19 of 33 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025ToolScope: Enhancing LLM Agent Tool Use through Tool Merging and Context-Aware Filtering22 Oct
  2. 2025MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers20 Aug
  3. 2025PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Play18 Mar
  4. 2024From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions10 Oct
  5. 2024AnyTool: Self-Reflective, Hierarchical Agents for Large-Scale API Calls6 Feb
  6. 2024EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction11 Jan
  7. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  8. 2023Large Language Models as Tool Makers26 May
  9. 2023Gorilla: Large Language Model Connected with Massive APIs24 May
  10. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs14 Apr
  11. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb

Other references · 8

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  2. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  3. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
  4. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Modelscited by 398
  5. 2023CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsetscited by 129
  6. 2024Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrievalcited by 52
  7. 2025MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP Usecited by 39
  8. 2025ToolMem: Enhancing Multimodal Agents with Learnable Tool Capability Memorycited by 14

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Learning from Failures: Heterogeneous Graph Memory for Small Language Model Tool-Using Agents
  2. 2025Unifying Dynamic Tool Creation and Cross-Task Experience Sharing through Cognitive Memory Architecture
  3. 2026JTPRO: A Joint Tool-Prompt Reflective Optimization Framework for Language Agents
  4. 2026ReCache: Efficient KV Cache Reuse and Compression for Tool-Augmented LLM Agents
  5. 2026Forgotten in Weights, Recovered by Tools: Agentic Tool Unlearning for LLM Agents
  6. 2026Toolcompass: Guiding Tool Trialing, Not Suppressing It
  7. 2026DOCSCHISEL: Adaptive Tool Documentation Optimization Framework for LLM Agents
  8. 2026Tools Are Not Islands: Set-Level Tool Retrieval for LLM Agents via Query-Conditioned Hyperedge Prediction