Pith. sign in

Toollibgen: Scalable automatic tool creation and aggregation for llm reasoning.arXiv preprint arXiv:2510.07768

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

Generative Skill Composition for LLM Agents

cs.CL · 2026-06-30 · unverdicted · novelty 7.0

SkillComposer performs task-conditioned skill sequence prediction with a constrained autoregressive decoder to jointly output skill subset, count, and order, raising pass rates by 23.1 and 18.2 percentage points on two production coding agents over no-skill baselines.

citing papers explorer

Showing 2 of 2 citing papers.

  • Generative Skill Composition for LLM Agents cs.CL · 2026-06-30 · unverdicted · none · ref 40

    SkillComposer performs task-conditioned skill sequence prediction with a constrained autoregressive decoder to jointly output skill subset, count, and order, raising pass rates by 23.1 and 18.2 percentage points on two production coding agents over no-skill baselines.

  • ReaComp: Compiling LLM Reasoning into Symbolic Solvers for Efficient Program Synthesis cs.CL · 2026-05-06 · unverdicted · none · ref 13

    LLM reasoning traces can be compiled into reusable symbolic solvers that achieve high accuracy on program synthesis benchmarks at zero inference cost and transfer to other domains.