MaDI-Bench supplies the first end-to-end benchmark tasks for full relational data integration pipelines across domains plus a variant-generation method to slow saturation.
Large language model-based data science agent: A survey
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
dataset 1
citation-polarity summary
years
2026 8representative citing papers
BioXArena benchmarks LLM agents on generating end-to-end ML pipelines for 76 multi-modal biomedical tasks, with MLEvolve plus Gemini-3.1-Pro scoring highest at 0.666.
DataPRM is an environment-aware generative process reward model that improves LLM data analysis agents by 7-11% on benchmarks via active verification and reflection-aware ternary rewards.
EvoDS adds autonomous skill acquisition via synthesis-validation-reuse and adaptive context compression via learned control within a two-stage multi-agent RL scheme, claiming 28.9% average gains over prior agents on four benchmarks plus elimination of out-of-token failures.
Automatically optimizing agent skill files on a branching lakehouse improved held-out validation accuracy by 31.9% on 25 synthetic-but-trace-anchored tasks.
MACA frames multi-agent coordination as posterior inference, learns a structural prior to guide orchestration, and reports 8.42% higher performance with 43.19% fewer tokens than adaptive baselines on benchmarks.
DataCOPE uses verifier-guided contrastive distillation from agent trajectories to discover skills, yielding average gains of 9.71% on report-style and 32.30% on reasoning-style data analysis tasks across four model settings.
Full-horizon planning with on-demand replanning achieves accuracy parity with single-step planning in tool-calling agents for knowledge base and multi-hop question answering while consuming 2-3 times fewer tokens.
citing papers explorer
-
MaDI-Bench: An End-to-End Data Integration Benchmark
MaDI-Bench supplies the first end-to-end benchmark tasks for full relational data integration pipelines across domains plus a variant-generation method to slow saturation.
-
BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks
BioXArena benchmarks LLM agents on generating end-to-end ML pipelines for 76 multi-modal biomedical tasks, with MLEvolve plus Gemini-3.1-Pro scoring highest at 0.666.
-
Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis
DataPRM is an environment-aware generative process reward model that improves LLM data analysis agents by 7-11% on benchmarks via active verification and reflection-aware ternary rewards.
-
EvoDS: Self-Evolving Autonomous Data Science Agent with Skill Learning and Context Management
EvoDS adds autonomous skill acquisition via synthesis-validation-reuse and adaptive context compression via learned control within a two-stage multi-agent RL scheme, claiming 28.9% average gains over prior agents on four benchmarks plus elimination of out-of-token failures.
-
"Skill Issues'': Data-Centric Optimization of Lakehouse Agents
Automatically optimizing agent skill files on a branching lakehouse improved held-out validation accuracy by 31.9% on 25 synthetic-but-trace-anchored tasks.
-
Multi-Agent Coordination Adaptation via Structure-Guided Orchestration
MACA frames multi-agent coordination as posterior inference, learns a structural prior to guide orchestration, and reports 8.42% higher performance with 43.19% fewer tokens than adaptive baselines on benchmarks.
-
Unsupervised Skill Discovery for Agentic Data Analysis
DataCOPE uses verifier-guided contrastive distillation from agent trajectories to discover skills, yielding average gains of 9.71% on report-style and 32.30% on reasoning-style data analysis tasks across four model settings.
-
Do Agents Need to Plan Step-by-Step? Rethinking Planning Horizon in Data-Centric Tool Calling
Full-horizon planning with on-demand replanning achieves accuracy parity with single-step planning in tool-calling agents for knowledge base and multi-hop question answering while consuming 2-3 times fewer tokens.