SPARK: Skeleton-Guided Reasoning Synthesis from Large-Scale Scientific Literature

arXiv:2608.30214 · cs.AI · Submitted 2026-08-31 · Read on arXiv

cs.AI

Submitted: 2026-08-31

Updated: 2026-08-31

Comments: 24 pages, 15 figures

Code: https://github.com/GAIR-NLP/lm-open-science-evaluation

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Benchmark — 38× in this paper · explained in 2 episodes
• Core — 26× in this paper · explained in 2 episodes
• Fine-Tuning — 9× in this paper · explained in 5 episodes
• Calibration — 8× in this paper · explained in 7 episodes
• Consistency — 8× in this paper · explained in 3 episodes
• Verification — 7× in this paper · explained in 2 episodes
• Ablation — 5× in this paper · explained in 1 episode
• Grounding — 5× in this paper · explained in 3 episodes
• Benchmarking — 3× in this paper · explained in 3 episodes
• Embeddings — 3× in this paper · explained in 2 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Decoupling — 2× in this paper · explained in 2 episodes
• Provenance — 2× in this paper · explained in 3 episodes
• Reasoning Traces — 2× in this paper · explained in 3 episodes
• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• Abstraction — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Annotator Agreement — 1× in this paper · explained in 1 episode
• Clustering — 1× in this paper · explained in 2 episodes
• Cosine Similarity — 1× in this paper · explained in 3 episodes
• DFT Calculations — 1× in this paper · explained in 2 episodes
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• Hallucination — 1× in this paper · explained in 3 episodes
• Human Assessment — 1× in this paper
• Instruction Tuning — 1× in this paper · explained in 2 episodes
• Inter-Annotator Agreement — 1× in this paper
• LLM judge — 1× in this paper · explained in 2 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Mode Collapse — 1× in this paper · explained in 2 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• RAG — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Training Verifiers to Solve Math Word Problems
• From Local to Global: A Graph RAG Approach to Query-Focused Summarization
• MegaScience: Pushing the Frontiers of Post-Training Datasets for Science Reasoning
• The Vendi Score: A Diversity Evaluation Metric for Machine Learning
• OpenDataArena: A Fair and Open Arena for Benchmarking Post-Training Dataset Value
• The Llama 3 Herd of Models
• Measuring Massive Multitask Language Understanding
• Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning
• SCP-116K: A High-Quality Problem-Solution Dataset and a Generalized Pipeline for Automated Extraction in the Higher Education Science Domain
• Are large language models superhuman chemists?
• gpt-oss-120b & gpt-oss-20b Model Card
• Galactica: A Large Language Model for Science
• SciQAG: A Framework for Auto-Generated Science Question Answering Dataset with Fine-grained Evaluation
• ResearchGPT: Benchmarking and Training LLMs for End-to-End Computer Science Research Workflows
• Qwen3 Technical Report
• ChemLLM: A Chemical Large Language Model
• Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems