CORE: Collaborative Reasoning via Cross Teaching

• URL: http://arxiv.org/abs/2601.21600v1
• Date: Thu, 29 Jan 2026 12:07:54 GMT
• Title: CORE: Collaborative Reasoning via Cross Teaching
• Abstract summary: Collaborative Reasoning (CORE) is a training-time collaboration framework that converts peer success into a learning signal.<n>We evaluate CORE across four standard reasoning datasets GSM8K, MATH, AIME, and GPQA.
• Score: 11.841736034560187
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models exhibit complementary reasoning errors: on the same instance, one model may succeed with a particular decomposition while another fails. We propose Collaborative Reasoning (CORE), a training-time collaboration framework that converts peer success into a learning signal via a cross-teaching protocol. Each problem is solved in two stages: a cold round of independent sampling, followed by a contexted rescue round in which models that failed receive hint extracted from a successful peer. CORE optimizes a combined reward that balances (i) correctness, (ii) a lightweight DPP-inspired diversity term to reduce error overlap, and (iii) an explicit rescue bonus for successful recovery. We evaluate CORE across four standard reasoning datasets GSM8K, MATH, AIME, and GPQA. With only 1,000 training examples, a pair of small open source models (3B+4B) reaches Pass@2 of 99.54% on GSM8K and 92.08% on MATH, compared to 82.50% and 74.82% for single-model training. On harder datasets, the 3B+4B pair reaches Pass@2 of 77.34% on GPQA (trained on 348 examples) and 79.65% on AIME (trained on 792 examples), using a training-time budget of at most 1536 context tokens and 3072 generated tokens. Overall, these results show that training-time collaboration can reliably convert model complementarity into large gains without scaling model size.

Related papers

• Models for minimalist RAG: B1ade 335M Embedding and 1B Parameter Small Language Models [2.1665689529884697]
  We present B1ade, an efficient RAG architecture comprising two purpose-built components: a compact embedding model and a purpose-built SLM.<n>B1ade-embed, a 335M parameter retrieval model constructed via parameter-free fusion of five pretrained encoders achieves top MTEB scores among sub-500M models with zero additional training.<n>B1ade-1B cites retrieved passages in 42.4% of responses, exceeding the attribution rate of its training distribution by 5.5 percentage points.
  arXiv  Detail & Related papers  (2026-07-29T22:41:25Z)
• Automated Proving of Shannon-Type Entropy Inequalities via Fine-Tuned Language Models and Guided Tree Search [50.16356451328644]
  Proving Shannon-type entropy inequalities is a fundamental task in information theory.<n>We investigate whether small-scale large language models, fine-tuned on atomic proof steps, can automate this process.<n>We show that GPT-5.5 solves 1.7% samples under zero-shot prompting while Psitip solves 33.3% samples.
  arXiv  Detail & Related papers  (2026-06-04T05:43:12Z)
• Off-the-Shelf LLMs as Process Scorers: Training-Free Alternative to PRMs for Mathematical Reasoning [51.88950852117154]
  Chunk-Level Guided Generation is a training-free alternative that uses an off-the-shelf large language model as a process scorer.<n>We show that scoring variable-length reasoning steps with large-model likelihoods is unreliable due to a systematic length bias.<n>Chunk-Level Guided Generation produces substantially shorter reasoning traces than PRM guided search.
  arXiv  Detail & Related papers  (2026-06-01T04:43:36Z)
• Three Roles, One Model: Role Orchestration at Inference Time to Close the Performance Gap Between Small and Large Agents [0.4666493857924357]
  We study whether inference-time scaffolding alone, without any additional training compute, can improve the performance of a small model in complex multi-step environments.<n>We evaluate Qwen3-8B on the AppWorld benchmark under both full-precision and 4-bit quantized configurations.<n>On full-precision inference, our scaffolded 8B model surpasses DeepSeek-Coder 33B Instruct (7.1%) from the original AppWorld evaluation.
  arXiv  Detail & Related papers  (2026-04-13T13:40:33Z)
• Correct, Concise and Complete: Multi-stage Training For Adaptive Reasoning [11.179446105672461]
  We propose a multi-stage efficient reasoning method that combines supervised fine-tuning and reinforcement learning.<n>Our approach reduces response length by an average of 28% for 8B models and 40% for 32B models.<n>It achieves a superior trade-off compared to more complex state-of-the-art efficient reasoning methods.
  arXiv  Detail & Related papers  (2026-01-06T12:31:51Z)
• SPARK: Stepwise Process-Aware Rewards for Reference-Free Reinforcement Learning [39.1720897614261]
  Process reward models (PRMs) that provide dense, step-level feedback have shown promise for reinforcement learning.<n>We propose SPARK: a three-stage framework where in the first stage a generator model produces diverse solutions and a verifier model evaluates them.<n>We show that aggregating multiple independent verifications at the step level produces training data for process reward models that surpass ground-truth outcome supervision.
  arXiv  Detail & Related papers  (2025-12-02T21:30:47Z)
• Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correction [95.91743732150233]
  Goedel-Prover-V2, a series of open-source language models, set a new state-of-the-art in automated theorem proving.<n>We generate synthetic tasks of increasing difficulty to train the model to master increasingly complex theorems.<n>Goedel-Prover-V2-32B achieves 88.1% on MiniF2F at pass@32 in standard mode and 90.4% in self-correction mode.
  arXiv  Detail & Related papers  (2025-08-05T16:28:22Z)
• Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining [72.7687229261317]
  'Breaking the Batch Barrier' (B3) is a novel batch construction strategy designed to curate high-quality batches for Contrastive Learning (CL)<n>Our method sets a new state-of-the-art, outperforming previous best methods by +1.3 and +2.9 points at the 7B and 2B model scales.<n> Notably, models trained with B3 surpass existing state-of-the-art results even with a batch size as small as 64, which is 4-16x smaller than that required by other methods.
  arXiv  Detail & Related papers  (2025-05-16T14:25:43Z)
• Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning [65.2421542320293]
  Reasoning abilities are crucial components of general intelligence.<n>Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning tasks.<n>This paper proposes a new RL framework, termed OREAL, to pursue the performance limit that can be achieved through textbfOutcome textbfREwtextbfArd-based reinforcement textbfLearning for mathematical reasoning tasks.
  arXiv  Detail & Related papers  (2025-02-10T18:57:29Z)
• Unsupervised Dense Retrieval with Relevance-Aware Contrastive Pre-Training [81.3781338418574]
  We propose relevance-aware contrastive learning. We consistently improve the SOTA unsupervised Contriever model on the BEIR and open-domain QA retrieval benchmarks. Our method can not only beat BM25 after further pre-training on the target corpus but also serves as a good few-shot learner.
  arXiv  Detail & Related papers  (2023-06-05T18:20:27Z)
• COLO: A Contrastive Learning based Re-ranking Framework for One-Stage Summarization [84.70895015194188]
  We propose a Contrastive Learning based re-ranking framework for one-stage summarization called COLO. COLO boosts the extractive and abstractive results of one-stage systems on CNN/DailyMail benchmark to 44.58 and 46.33 ROUGE-1 score.
  arXiv  Detail & Related papers  (2022-09-29T06:11:21Z)
• CaCo: Both Positive and Negative Samples are Directly Learnable via Cooperative-adversarial Contrastive Learning [45.68097757313092]
  We train an encoder by distinguishing positive samples from negative ones given query anchors. We show that the positive and negative samples can be cooperatively and adversarially learned by minimizing and maximizing the contrastive loss. The proposed method achieves 71.3% and 75.3% in top-1 accuracy respectively over 200 and 800 epochs of pre-training ResNet-50 backbone on ImageNet1K.
  arXiv  Detail & Related papers  (2022-03-27T18:50:39Z)
• Fast Uncertainty Quantification for Deep Object Pose Estimation [91.09217713805337]
  Deep learning-based object pose estimators are often unreliable and overconfident. In this work, we propose a simple, efficient, and plug-and-play UQ method for 6-DoF object pose estimation.
  arXiv  Detail & Related papers  (2020-11-16T06:51:55Z)

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.