Pith. sign in

REVIEW 11 cited by

CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2305.14318 v3 pith:F6OZSZV4 submitted 2023-05-23 cs.CL

CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models

classification cs.CL
keywords creationtoolcreatorllmsabilitydiverseabstractconcrete
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Large Language Models (LLMs) have made significant progress in utilizing tools, but their ability is limited by API availability and the instability of implicit reasoning, particularly when both planning and execution are involved. To overcome these limitations, we propose CREATOR, a novel framework that enables LLMs to create their own tools using documentation and code realization. CREATOR disentangles abstract tool creation and concrete decision execution, resulting in improved performance. We evaluate CREATOR on MATH and TabMWP benchmarks, respectively consisting of challenging math competition problems and diverse tabular contents. Remarkably, CREATOR outperforms existing chain-of-thought, program-of-thought, and tool-using baselines. Additionally, we introduce the Creation Challenge dataset, featuring 2K diverse questions, to emphasize the necessity and benefits of LLMs' tool creation ability. Further research demonstrates that leveraging LLMs as tool creators facilitates knowledge transfer, and LLMs exhibit varying levels of tool creation abilities, enabling them to adapt to diverse situations. The tool creation ability revolutionizes the LLM's problem-solving paradigm, driving us closer to the next frontier of artificial intelligence. All the codes and data are released.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution

    cs.CL 2023-09 unverdicted novelty 8.0

    Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.

  2. API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs

    cs.CL 2023-04 conditional novelty 8.0

    API-Bank is a new benchmark and training dataset for tool-augmented LLMs that shows fine-tuned models can approach GPT-3.5 tool-use effectiveness.

  3. SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces

    cs.CR 2026-05 unverdicted novelty 7.0

    SkillSafetyBench is a benchmark of 155 cases across 47 tasks and 6 risk domains showing that non-user attacks via skills, artifacts, or environments can consistently induce unsafe agent behavior.

  4. Prompt Injection Attack to Tool Selection in LLM Agents

    cs.CR 2025-04 conditional novelty 7.0

    ToolHijacker optimizes malicious tool documents via a two-phase strategy to hijack LLM agents' tool selection in no-box settings.

  5. Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads

    cs.LG 2024-01 conditional novelty 7.0

    Medusa augments LLMs with multiple decoding heads and tree-based attention to predict and verify several tokens in parallel, yielding 2.2-3.6x inference speedup via two fine-tuning regimes.

  6. Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems

    cs.CL 2026-07 conditional novelty 6.0

    Compiling repeated SOP nodes into environment-grounded, versioned tools cuts production p50 latency by 42% and end-to-end error rate by up to 53% in a 44-node fulfillment-center alarm-triage agent.

  7. VESTA: Visual Exploration with Statistical Tool Agents

    cs.AI 2026-05 unverdicted novelty 6.0

    VESTA introduces dynamic tool creation for VLMs that outperforms static-tool and no-tool baselines on distribution fitting, time series, and astronomy tasks in the new DAWN benchmark.

  8. SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces

    cs.CR 2026-05 unverdicted novelty 6.0

    SkillSafetyBench shows that localized non-user attacks via skills and artifacts can consistently induce unsafe agent behavior across domains and model backends, independent of user intent.

  9. Querying Structured Data Through Natural Language Using Language Models

    cs.CL 2026-04 conditional novelty 6.0

    Fine-tuning an 8B LLM with synthetic data enables accurate natural language querying of structured datasets like accessibility services in Spain, generalizing to new locations.

  10. SoK: Agentic Skills -- Beyond Tool Use in LLM Agents

    cs.CR 2026-02 unverdicted novelty 6.0

    The paper systematizes agentic skills beyond tool use, providing design pattern and representation-scope taxonomies plus security analysis of malicious skill infiltration in agent marketplaces.

  11. SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills

    cs.AI 2026-06 unverdicted novelty 5.0

    SkillDisCo distills reusable PFSM subgraphs from successful agent traces and compiles them into callable procedural skills, improving success rates and reducing turns on ALFWorld and WebArena.