Bidirectional Curriculum Generation: A Multi-Agent Framework for Data-Efficient Mathematical Reasoning

• URL: http://arxiv.org/abs/2603.05120v1
• Date: Thu, 05 Mar 2026 12:49:21 GMT
• Title: Bidirectional Curriculum Generation: A Multi-Agent Framework for Data-Efficient Mathematical Reasoning
• Authors: Boren Hu, Xiao Liu, Boci Peng, Xinping Zhao, Xiaoran Shang, Yun Zhu, Lijun Wu,
• Abstract summary: We introduce a novel Bidirectional Curriculum Generation framework to maximize the instructional value of every training sample.<n>Unlike rigid trajectories, our multi-agent ecosystem mimics adaptive pedagogy to establish a closed feedback loop.<n>This mechanism ensures that the model consumes only the most effective data at any given stage.
• Score: 16.95900718416944
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Enhancing mathematical reasoning in Large Language Models typically demands massive datasets, yet data efficiency remains a critical bottleneck. While Curriculum Learning attempts to structure this process, standard unidirectional approaches (simple-to-complex) suffer from inefficient sample utilization: they blindly escalate complexity even when foundational gaps persist, leading to wasted computation on unsolvable problems. To maximize the instructional value of every training sample, we introduce a novel Bidirectional Curriculum Generation framework. Unlike rigid trajectories, our multi-agent ecosystem mimics adaptive pedagogy to establish a closed feedback loop. It dynamically generates data by either complicating problems to challenge the model or, crucially, simplying them to repair specific reasoning failures. This mechanism ensures that the model consumes only the most effective data at any given stage. Grounded in the Optimal Pacing Theorem, our approach optimizes the learning trajectory, significantly outperforming baselines while achieving superior reasoning performance with substantially fewer instruction samples.

Related papers

• SPaRFT: Self-Paced Reinforcement Fine-Tuning for Large Language Models [51.74498855100541]
  Large language models (LLMs) have shown strong reasoning capabilities when fine-tuned with reinforcement learning (RL)<n>We propose textbfSPaRFT, a self-paced learning framework that enables efficient learning based on the capability of the model being trained.
  arXiv  Detail & Related papers  (2025-08-07T03:50:48Z)
• Efficient Machine Unlearning via Influence Approximation [75.31015485113993]
  Influence-based unlearning has emerged as a prominent approach to estimate the impact of individual training samples on model parameters without retraining.<n>This paper establishes a theoretical link between memorizing (incremental learning) and forgetting (unlearning)<n>We introduce the Influence Approximation Unlearning algorithm for efficient machine unlearning from the incremental perspective.
  arXiv  Detail & Related papers  (2025-07-31T05:34:27Z)
• Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning [42.089912289949154]
  This paper presents Self-Error-Instruct (SEI), a framework that addresses model weaknesses and synthesizes more generalized targeted training data.<n>Specifically, we explore a target model on two mathematical datasets, GSM8K and MATH, to pinpoint bad cases.<n>Next, we sample a few bad cases during each generation for each identified error type and input them into the instructor model, which synthesizes additional training data.
  arXiv  Detail & Related papers  (2025-05-28T17:02:47Z)
• AdvKT: An Adversarial Multi-Step Training Framework for Knowledge Tracing [64.79967583649407]
  Knowledge Tracing (KT) monitors students' knowledge states and simulates their responses to question sequences.<n>Existing KT models typically follow a single-step training paradigm, which leads to significant error accumulation.<n>We propose a novel Adversarial Multi-Step Training Framework for Knowledge Tracing (AdvKT) which focuses on the multi-step KT task.
  arXiv  Detail & Related papers  (2025-04-07T03:31:57Z)
• Towards Accelerated Model Training via Bayesian Data Selection [45.62338106716745]
  We propose a more reasonable data selection principle by examining the data's impact on the model's generalization loss. Recent work has proposed a more reasonable data selection principle by examining the data's impact on the model's generalization loss. This work solves these problems by leveraging a lightweight Bayesian treatment and incorporating off-the-shelf zero-shot predictors built on large-scale pre-trained models.
  arXiv  Detail & Related papers  (2023-08-21T07:58:15Z)
• Towards Robust Dataset Learning [90.2590325441068]
  We propose a principled, tri-level optimization to formulate the robust dataset learning problem. Under an abstraction model that characterizes robust vs. non-robust features, the proposed method provably learns a robust dataset.
  arXiv  Detail & Related papers  (2022-11-19T17:06:10Z)
• HyperImpute: Generalized Iterative Imputation with Automatic Model Selection [77.86861638371926]
  We propose a generalized iterative imputation framework for adaptively and automatically configuring column-wise models. We provide a concrete implementation with out-of-the-box learners, simulators, and interfaces.
  arXiv  Detail & Related papers  (2022-06-15T19:10:35Z)
• Model-based Offline Imitation Learning with Non-expert Data [7.615595533111191]
  We propose a scalable model-based offline imitation learning algorithmic framework that leverages datasets collected by both suboptimal and optimal policies. We show that the proposed method textitalways outperforms Behavioral Cloning in the low data regime on simulated continuous control domains.
  arXiv  Detail & Related papers  (2022-06-11T13:08:08Z)
• DEALIO: Data-Efficient Adversarial Learning for Imitation from Observation [57.358212277226315]
  In imitation learning from observation IfO, a learning agent seeks to imitate a demonstrating agent using only observations of the demonstrated behavior without access to the control signals generated by the demonstrator. Recent methods based on adversarial imitation learning have led to state-of-the-art performance on IfO problems, but they typically suffer from high sample complexity due to a reliance on data-inefficient, model-free reinforcement learning algorithms. This issue makes them impractical to deploy in real-world settings, where gathering samples can incur high costs in terms of time, energy, and risk. We propose a more data-efficient IfO algorithm
  arXiv  Detail & Related papers  (2021-03-31T23:46:32Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.