Related papers: Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Math

Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Math

URL: http://arxiv.org/abs/2510.26143v1
Date: Thu, 30 Oct 2025 04:56:44 GMT
Title: Reasoning Curriculum: Bootstrapping Broad LLM Reasoning from Math
Authors: Bo Pang, Deqian Kong, Silvio Savarese, Caiming Xiong, Yingbo Zhou,
Abstract summary: Reasoning Curriculum first elicits reasoning skills in pretraining-aligned domains such as math, then adapts and refines these skills across other domains via joint RL.<n>The curriculum is minimal and backbone-agnostic, requiring no specialized reward models beyond standard verifiability checks.
Score: 79.75335577284747
License: http://creativecommons.org/licenses/by/4.0/
Abstract: Reinforcement learning (RL) can elicit strong reasoning in large language models (LLMs), yet most open efforts focus on math and code. We propose Reasoning Curriculum, a simple two-stage curriculum that first elicits reasoning skills in pretraining-aligned domains such as math, then adapts and refines these skills across other domains via joint RL. Stage 1 performs a brief cold start and then math-only RL with verifiable rewards to develop reasoning skills. Stage 2 runs joint RL on mixed-domain data to transfer and consolidate these skills. The curriculum is minimal and backbone-agnostic, requiring no specialized reward models beyond standard verifiability checks. Evaluated on Qwen3-4B and Llama-3.1-8B over a multi-domain suite, reasoning curriculum yields consistent gains. Ablations and a cognitive-skill analysis indicate that both stages are necessary and that math-first elicitation increases cognitive behaviors important for solving complex problems. Reasoning Curriculum provides a compact, easy-to-adopt recipe for general reasoning.

Related papers

On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models [73.10315509190623]
Recent reinforcement learning techniques have yielded impressive reasoning improvements in language models.<n>It remains unclear whether post-training truly extends a model's reasoning ability beyond what it acquires during pre-training.<n>We develop a fully controlled experimental framework that isolates the causal contributions of pre-training, mid-training, and RL-based post-training.
arXiv Detail & Related papers (2025-12-08T18:12:10Z)
Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training [76.12556589212666]
We show that curriculum post-training avoids the exponential complexity bottleneck.<n>Under outcome-only reward signals, reinforcement learning finetuning achieves high accuracy with sample complexity.<n>We establish guarantees for test-time scaling, where curriculum-aware querying reduces both reward oracle calls and sampling cost from exponential to order.
arXiv Detail & Related papers (2025-11-10T18:29:54Z)
Executable Counterfactuals: Improving LLMs' Causal Reasoning Through Code [29.382261465478248]
We introduce executable counterfactuals, a framework that operationalizes causal reasoning through code and math problems.<n>Our results reveal substantial drop in accuracy (25-40%) from interventional to counterfactual reasoning for SOTA models like o4-mini and Claude-4-Sonnet.<n>We also test whether a model trained on code would generalize to counterfactual math word problems.
arXiv Detail & Related papers (2025-10-02T00:26:35Z)
RL for Reasoning by Adaptively Revealing Rationales [36.50924054394857]
Supervised fine-tuning (SFT) relies on dense ground-truth labels, which become increasingly costly as sequence length grows.<n>We address this by adaptive backtracking (AdaBack), a per-sample curriculum learning algorithm that reveals only a partial prefix of the target output during training.<n>We show that our adaptive curriculum over partial answers reliably solves problems that are otherwise intractable.
arXiv Detail & Related papers (2025-06-22T17:46:14Z)
Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective [82.24301452333577]
Reinforcement learning (RL) has emerged as a promising approach to improve large language model (LLM) reasoning.<n>A key challenge lies in the lack of reliable, scalable RL reward signals across diverse reasoning domains.<n>We introduce Guru, a curated RL reasoning corpus of 92K verifiable examples spanning six reasoning domains.
arXiv Detail & Related papers (2025-06-17T20:24:00Z)
Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning [52.32193550674408]
We aim to improve the reasoning capabilities of language models via reinforcement learning (RL)<n>We propose to schedule tasks from easy to hard (E2H), allowing LLMs to build reasoning skills gradually.<n>E2H Reasoner significantly improves the reasoning ability of small LLMs (1.5B to 3B)
arXiv Detail & Related papers (2025-06-07T02:41:54Z)
Self-Evolving Curriculum for LLM Reasoning [96.10277986436172]
Self-Evolving Curriculum (SEC) is an automatic curriculum learning method that learns a curriculum policy concurrently with the RL fine-tuning process.<n>Our experiments demonstrate that SEC significantly improves models' reasoning capabilities, enabling better generalization to harder, out-of-distribution test problems.
arXiv Detail & Related papers (2025-05-20T23:17:15Z)
General Intelligence Requires Reward-based Pretraining [14.057301560895505]
Large Language Models (LLMs) have demonstrated impressive real-world utility.<n>But their ability to reason adaptively and robustly remains fragile.<n>We propose disangling knowledge and reasoning through three key directions.
arXiv Detail & Related papers (2025-02-26T18:51:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.