Papers
arxiv:2611.15178

HyperSkill: Training-Free Omnimodal GRPO via Hypergraph-Indexed Skill-Library Evolution

Published on Nov 11
Authors:
,
,
,

Abstract

Reinforcement learning sharpens LLM reasoning, but parameter updates are expensive, forgetful, and opaque; training-free libraries swap gradients for a textual store but still use trajectory-level, correlation-based admission and flat structure. To address both, we propose HyperSkill, a Training-Free Omnimodal GRPO framework that keeps the backbone frozen and replaces gradient updates with auditable edits to a Hypergraph-Indexed Skill-Library, where skills are advantage-bearing nodes and compositions are hyperedges. It has three components: training-time distillation admits counterfactually checked skills and learns a protocol skill from failures; gated hypergraph retrieval injects advantage-ranked skills where a per-dataset gate admits them; and an execution protocol makes the frozen backbone commit to an answer. On 11 text, vision-language, and omnimodal benchmarks, HyperSkill is best or tied on every dataset and beats the best baseline by 13.0 average F1 points while keeping the backbone frozen. Our software and data are publicly available at https://github.com/LHRLAB/HyperSkill.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2611.15178
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2611.15178 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2611.15178 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2611.15178 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.