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.
arXiv preprint arXiv:2510.05318 , year=
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
EnterpriseMem-Bench shows stateless multi-turn Text-to-SQL accuracy drops to zero by turn 3, working memory is the main driver of gains, and additional memory components yield model- and dataset-dependent effects from +14 to -16 percentage points.
PrepBench is a benchmark showing that state-of-the-art LLMs still struggle with natural-language-driven data preparation involving disambiguation, code generation, and workflow translation.
New Text-to-Big SQL metrics show that LLM agents must balance accuracy with cost and speed at scale, where GPT-4o trades some accuracy for up to 12x speedup and GPT-5.2 proves more cost-effective than Gemini 3 Pro on large inputs.
Reinforcement learning with a dual recall-precision reward trains models to enumerate valid interpretations and answers for ambiguous inputs using only multiple-answer supervision.
citing papers explorer
-
PrepBench: How Far Are We from Natural-Language-Driven Data Preparation?
PrepBench is a benchmark showing that state-of-the-art LLMs still struggle with natural-language-driven data preparation involving disambiguation, code generation, and workflow translation.