REVIEW 15 cited by
Light-R1: Curriculum SFT, DPO and RL for Long COT from Scratch and Beyond
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
This paper introduces Light-R1, an open-source suite for training long reasoning models using reproducible and cost-effective methodology. Given the proprietary nature of data used in the DeepSeek-R1 series, we develop an alternative approach leveraging exclusively public data and models. Our curriculum training progressively increases data difficulty, combined with multi-staged post-training. Our Light-R1-32B model, trained from Qwen2.5-32B-Instruct, outperforms DeepSeek-R1-Distill-Qwen-32B in math reasoning. Experimental results show that this curriculum approach becomes more effective when distinct, diverse datasets are available for different training stages: fine-tuning DeepSeek-R1-Distilled models (pre-tuned by DeepSeek team on proprietary data) with 3,000 challenging examples from our curriculum dataset yielded state-of-the-art 7B and 14B models, while the 32B model, Light-R1-32B-DS performed comparably to QwQ-32B and DeepSeek-R1. Furthermore, we extend our work by applying GRPO on long reasoning models. Our final Light-R1-14B-DS achieves SOTA performance among 14B models in math, with AIME24 & 25 scores of 74.0 and 60.2 respectively, surpassing many 32B models and DeepSeek-R1-Distill-Llama-70B. Despite math-focused training, Light-R1-14B-DS demonstrates strong cross-domain generalization. Light-R1 represents a significant advancement in making sophisticated reasoning models more accessible and implementable in real-world applications. Our models, training data and code have been made available at https://github.com/Qihoo360/Light-R1.
Forward citations
Cited by 15 Pith papers
-
Sticker-TTS: Learn to Utilize Historical Experience with a Sticker-driven Test-Time Scaling Framework
Sticker-TTS uses three collaborating models to distill and reuse compact summaries (stickers) of past reasoning attempts, improving math benchmark accuracy at a claimed equivalent inference cost.
-
Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning
Training a Qwen2.5-7B model with GRPO on math and puzzle data improves both domains, code transfer depends on the starting model, and template or reward mismatches sharply hurt performance.
-
Squeeze the Soaked Sponge: Efficient Off-policy Reinforcement Finetuning for Large Language Model
ReMix cuts reinforcement finetuning rollout volume by 30x to 450x on math reasoning by mixing historical and on-policy data with a convex KL constraint and a mid-training switch to on-policy updates.
-
MiCoTA: Bridging the Learnability Gap with Intermediate CoT and Teacher Assistants
Training small language models on intermediate-length reasoning chains from a merged mid-sized teacher assistant improves their math reasoning scores over direct distillation from a large teacher.
-
A Model Can Help Itself: Reward-Free Self-Training for LLM Reasoning
SePT enables LLMs to improve math reasoning on multiple benchmarks by iteratively training on their own low-temperature generated responses using an online data refresh mechanism.
-
Domain-Aware RAG: MoL-Enhanced RL for Efficient Training and Scalable Retrieval
A two-stage RAG training pipeline, MoL continual pre-training plus GRPO reinforcement learning with single-passage training and multi-passage inference, reports state-of-the-art retrieval recall on NFCORPUS and SCIFAC...
-
Uncertainty Under the Curve: A Sequence-Level Entropy Area Metric for Reasoning LLM
Entropy Area Score sums token-level predictive entropy across a reasoning sequence, correlates with answer entropy, and selects SFT training data better than Pass Rate filtering in limited AIME experiments.
-
ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models
An open training recipe that teaches a 32B LLM to reason in three adjustable modes, cutting token use by half or three quarters with small accuracy losses.
-
REST: Stress Testing Large Reasoning Models by Asking Multiple Problems at Once
Asking a reasoning model several problems at once reveals large accuracy drops and exposes differences that single-question benchmarks miss.
-
Enhancing Large Language Models through Structured Reasoning
Structured reasoning tags plus a max-flow reward let a 1.5B model match the math accuracy of models trained for far longer, but the gains are within statistical noise.
-
AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy
A 7B reasoning model trained with carefully balanced SFT and RL beats prior small models on math and code benchmarks, with the paper documenting scaling and temperature heuristics.
-
SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning
SwS uses failures during RL training to synthesize targeted math problems, improving reasoning accuracy on eight benchmarks.
-
A Practical Two-Stage Recipe for Mathematical LLMs: Maximizing Accuracy with SFT and Efficiency with Reinforcement Learning
Ten-epoch SFT then GRPO raises AIME/MATH-500 accuracy while reducing solution length, achieving 8th place on AIMO's private set.
-
Schema-R1: A reasoning training approach for schema linking in Text-to-SQL Task
Schema-R1 combines cold-start SFT on 200 CoT samples with GRPO rule-based RL, reporting table and column filter accuracy gains of 10 percentage points or more over a fine-tuned baseline on Spider-dev.
-
Towards Concise and Adaptive Thinking in Large Reasoning Models: A Survey
A comprehensive review that categorizes methods for shortening and adaptively triggering chain-of-thought reasoning in large language models.
Discussion (0). Sign in to comment.