A multi-agent framework reconstructs the evolutionary graph of post-training LLM datasets, revealing domain patterns like vertical refinement in math data and systemic issues like redundancy and benchmark contamination, then applies it to create a more diverse lineage-aware dataset.
Megascience: Pushing the frontiers of post-training datasetsforsciencereasoning.arXivpreprint
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
dataset 2
background 1
citation-polarity summary
representative citing papers
Post-training stages reshape generalization in biological reasoning models distinctly: CPT aligns with biological language, SFT boosts ID performance but causes OOD to peak early and decline, while RL on strong SFT checkpoints can recover OOD generalization.
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.
CrystalReasoner combines LLM reasoning traces with physical priors and multi-objective RL to generate valid, stable, and property-conditioned crystal structures.
Rubric-based RL verifiers can be gamed via partial criterion satisfaction and implicit-to-explicit tricks, yielding proxy gains that do not improve quality under rubric-free judges; stronger verifiers reduce but do not eliminate the mismatch.
SOD reweights on-policy distillation strength step-by-step using divergence to stabilize tool use in small language model agents, yielding up to 20.86% gains and 26.13% on AIME 2025 for a 0.6B model.
MiroThinker shows that scaling agent-environment interactions via reinforcement learning lets a 72B open-source model reach up to 81.9% on GAIA and approach commercial performance on research benchmarks.
SlimSearcher reduces tool-call rounds by 17-58% on GAIA, BrowseComp and XBenchDeepSearch while maintaining accuracy via Pareto filtration in SFT and Adaptive Reward Gating in RL.
FitOne-8B/32B models improve average scores on ACSM-EP and NSCA-CSCS certification exams by up to 12.73% over base Qwen3 while retaining general capabilities.
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
citing papers explorer
-
Tracing the Roots: A Multi-Agent Framework for Uncovering Data Lineage in Post-Training LLMs
A multi-agent framework reconstructs the evolutionary graph of post-training LLM datasets, revealing domain patterns like vertical refinement in math data and systemic issues like redundancy and benchmark contamination, then applies it to create a more diverse lineage-aware dataset.
-
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
SR²AM achieves competitive Pass@1 accuracy on diverse tasks with 25.8-95.3% fewer reasoning tokens than much larger models by using self-regulated simulative planning trained via supervised learning and RL.
-
CrystalReasoner: Reasoning and RL for Property-Conditioned Crystal Structure Generation
CrystalReasoner combines LLM reasoning traces with physical priors and multi-objective RL to generate valid, stable, and property-conditioned crystal structures.
-
Reward Hacking in Rubric-Based Reinforcement Learning
Rubric-based RL verifiers can be gamed via partial criterion satisfaction and implicit-to-explicit tricks, yielding proxy gains that do not improve quality under rubric-free judges; stronger verifiers reduce but do not eliminate the mismatch.
-
Enhancing Fitness Intelligence through Domain-Specific LLM Post-Training
FitOne-8B/32B models improve average scores on ACSM-EP and NSCA-CSCS certification exams by up to 12.73% over base Qwen3 while retaining general capabilities.