mlsanityData to 7 Oct 2026

Toolken+: Improving LLM Tool Usage with Reranking and a Reject Option

arXiv 2410.12004 ↗First posted 15 Oct 2024cs.CLcited by 3

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

Abstract (arXiv)

The recently proposed ToolkenGPT tool learning paradigm demonstrates promising performance but suffers from two major issues: first, it cannot benefit from tool documentation, and second, it often makes mistakes in whether to use a tool at all. We introduce Toolken+ that mitigates the first problem by reranking top k tools selected by ToolkenGPT and the second problem with a special "Reject" option such that the model will generate a vocabulary token if "Reject" is ranked first. We demonstrate the effectiveness of Toolken+ on multistep numerical reasoning and tool selection tasks.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use. Builds on 18 of its 28 references that are in the map. First posted on arXiv 15 Oct 2024.

Builds on

18 of 28 references.

Closest ancestors · 6

Same direction, newest first

  1. 2023MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use4 Oct
  2. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs31 Jul
  3. 2023GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction30 May
  4. 2023Gorilla: Large Language Model Connected with Massive APIs24 May
  5. 2023ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings19 May
  6. 2023Toolformer: Language Models Can Teach Themselves to Use Tools9 Feb

Other references · 12

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  4. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  5. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  6. 2022Least-to-Most Prompting Enables Complex Reasoning in Large Language Modelscited by 1,397
  7. 2023CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquingcited by 751
  8. 2020Long Range Arena: A Benchmark for Efficient Transformerscited by 696
  9. 2022Large Language Models Can Self-Improvecited by 656
  10. 2018VirtualHome: Simulating Household Activities via Programscited by 411
  11. 2023REFINER: Reasoning Feedback on Intermediate Representationscited by 203
  12. 2023Augmenting Large Language Model Translators via Translation Memoriescited by 21

Built on by

Cited by year

Citing papers per year: 2025: 3.

3 papers.

  1. 2025Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directionscited by 257
  2. 2025Schema as Parameterized Tools for Universal Information Extractioncited by 2
  3. 2025Fast, Slow, and Tool-augmented Thinking for LLMs: A Reviewcited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2024ToolRerank: Adaptive and Hierarchy-Aware Reranking for Tool Retrieval
  2. 2026Try, Check and Retry: A Divide-and-Conquer Framework for Boosting Long-context Tool-Calling Performance of LLMs
  3. 2024Meta-Reasoning Improves Tool Use in Large Language Models
  4. 2024Tool Learning with Large Language Models: A Survey
  5. 2025Verification-Guided Context Optimization for Tool Calling via Hierarchical LLMs-as-Editors
  6. 2025RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation
  7. 2024RoTBench: A Multi-Level Benchmark for Evaluating the Robustness of Large Language Models in Tool Learning
  8. 2024TOOLVERIFIER: Generalization to New Tools via Self-Verification