pith. sign in

Title resolution pending

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

4 Pith papers citing it

years

2026 3 2025 1

representative citing papers

SkillDroid: Compile Once, Reuse Forever

cs.HC · 2026-04-16 · conditional · novelty 6.0

SkillDroid compiles LLM-guided GUI trajectories into parameterized skill templates and replays them via a matching cascade, reaching 85.3% success rate with 49% fewer LLM calls and improving from 87% to 91% over 150 rounds while the stateless baseline drops to 44%.

Governance by Construction for Generalist Agents

cs.AI · 2026-05-20 · unverdicted · novelty 5.0

CUGA introduces a runtime governance architecture that enforces policies at five checkpoints in generalist agent execution pipelines for predictable and compliant behavior.

citing papers explorer

Showing 4 of 4 citing papers.

  • SQuTR: A Robustness Benchmark for Spoken Query to Text Retrieval under Acoustic Noise cs.IR · 2026-02-13 · unverdicted · none · ref 38

    SQuTR aggregates 37k queries from six text retrieval datasets, synthesizes speech from 200 speakers, adds 17 noise categories at varying SNR, and shows that even large retrieval models degrade sharply under extreme acoustic noise.

  • SkillDroid: Compile Once, Reuse Forever cs.HC · 2026-04-16 · conditional · none · ref 21

    SkillDroid compiles LLM-guided GUI trajectories into parameterized skill templates and replays them via a matching cascade, reaching 85.3% success rate with 49% fewer LLM calls and improving from 87% to 91% over 150 rounds while the stateless baseline drops to 44%.

  • LEAF: Knowledge Distillation of Text Embedding Models with Teacher-Aligned Representations cs.IR · 2025-09-16 · conditional · none · ref 40

    LEAF distills teacher-aligned student embedding models that achieve new SOTA results on BEIR and MTEB for their size class while requiring only modest data and compute.

  • Governance by Construction for Generalist Agents cs.AI · 2026-05-20 · unverdicted · none · ref 24

    CUGA introduces a runtime governance architecture that enforces policies at five checkpoints in generalist agent execution pipelines for predictable and compliant behavior.