Compete Then Collaborate: Frontier AI Teachers Build a Verifiable Curriculum to Improve a Coding Student Beyond Imitation

• URL: http://arxiv.org/abs/2607.08255v1
• Date: Thu, 09 Jul 2026 09:00:52 GMT
• Title: Compete Then Collaborate: Frontier AI Teachers Build a Verifiable Curriculum to Improve a Coding Student Beyond Imitation
• Abstract summary: We introduce a compete-then-collaborate framework where four frontier AI teachers are ranked head-to-head by an execution-based judge.<n>Using the same collaborative curriculum as a reinforcement learning with verifiable rewards (RLVR) environment improves the student.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models increasingly serve as teachers generating training data for smaller students. Prior multi-teacher knowledge distillation methods merge outputs without determining which frontier model teaches best, often relying on an LLM judge biased toward its own outputs. We introduce a compete-then-collaborate framework where four frontier AI teachers (Claude, Codex-GPT, Grok, Gemini) are ranked head-to-head by an execution-based judge (unit tests and stdin-stdout checks) with fairness controls, and then collaborate to build a verifiable curriculum for a student (Qwen2.5-Coder). We report three findings. (1) Under execution verification, all teachers solve standard problems near-perfectly after self-correction (99-100%) due to a saturation effect, but harder competition problems separate them (Gemini 77% > Claude 69% = Codex 69% > Grok 50%); however, the robust student-side results do not depend on teacher ranking. (2) Imitation (SFT) on verified solutions does not improve, and can degrade, an already-competent student at 7B and 32B (e.g., from 76.7% to 72.7% on MBPP-test, and 5.9% to 2.9% on competition problems). (3) Using the same collaborative curriculum as a reinforcement learning with verifiable rewards (RLVR) environment improves the student (from 5.9% to 8.8% peak on competition problems, a +49% relative gain), reversing SFT's direction. The value of AI-teacher collaboration lies not in pooling answers to imitate, but in jointly constructing a verifiable environment where the student learns by doing. We release a reproducible on-prem pipeline (NVIDIA GB10) with framework patches for running GRPO on a bleeding-edge stack.

Related papers

• Data-free On-policy Distillation [49.537587070291444]
  On-policy distillation (OPD) has become a standard component of frontier post-training pipelines.<n>But how much its training data actually contributes has gone largely unexamined.<n>We take this to its limit with Data-free On-policy Distillation (DF-OPD)<n>DF-OPD matches and even surpasses real data, and the questions it produces track the teacher's own post-training data.
  arXiv  Detail & Related papers  (2026-09-12T23:51:35Z)
• Beyond the Best Teacher: Expanding and Compressing the Reasoning Solution Manifold [4.090731563364332]
  We argue that reinforcement learning policies should be viewed as local probes of a multi-basin reasoning solution manifold.<n>We propose an expand-then-compress framework that couples teacher construction with multi-teacher policy distillation.
  arXiv  Detail & Related papers  (2026-07-30T07:05:37Z)
• OPOD: On-Policy Omni Distillation [55.440058537827134]
  Training a single model on pooled multimodal data often fails to match models specialized for individual modalities.<n>We present On-Policy Omni Distillation (OPD), which routes each student response to the matching text, image, or audio teacher.<n>OPD achieves the best average score at every scale, reaching 70.8, 51.7, and 46.2.
  arXiv  Detail & Related papers  (2026-07-23T04:55:04Z)
• EduGuard: A Safe RAG-Based LLM Tutor for Programming Education [1.2999518604217852]
  Generative AI (GenAI) is increasingly used by students for programming explanation, debug, and assignment support.<n>This paper presents EduGuard, a safe retrieval-augmented generation (RAG) tutoring framework for introductory programming.<n>EduGuard integrates query understanding, instructor-approved course retrieval, pedagogical strategy selection, rubric-aware generation, claim-level verification, and overreliance control.
  arXiv  Detail & Related papers  (2026-07-17T08:18:18Z)
• Knowledge Distillation from Large Reasoning Models to Compact Student Models: A Case Study on the John O Bryan Mathematics Competition [0.0]
  We build a Chain-of-Thought training corpus through a dual-agent framework.<n>The dataset is used to fine-tune the student model with Low-Rank Adaptation (LoRA) on Apple Silicon hardware.
  arXiv  Detail & Related papers  (2026-06-30T02:34:45Z)
• AcademiClaw: When Students Set Challenges for AI Agents [69.70303995121154]
  AcademiClaw is a benchmark of 80 complex, long-horizon tasks sourced directly from university students' real academic disconnects.<n>We show that even the best of models achieves only a 55% pass rate.<n>We hope that AcademiClaw and its open-sourced data and code can serve as a useful resource for the OpenClaw community.
  arXiv  Detail & Related papers  (2026-05-04T14:40:42Z)
• CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution [52.691495954442985]
  CoVerRL is a framework where a single model alternates between generator and verifier roles, with each capability bootstrapping the other.<n> Experiments across Qwen and Llama model families demonstrate that CoVerRL outperforms label-free baselines by 4.7-5.9% on mathematical reasoning benchmarks.<n>Self-verification accuracy improves from around 55% to over 85%, confirming that both capabilities genuinely co-evolve.
  arXiv  Detail & Related papers  (2026-03-18T14:38:55Z)
• GATES: Self-Distillation under Privileged Context with Consensus Gating [89.62339954332248]
  We study self-distillation in settings where supervision is unreliable.<n>We focus on document-grounded question answering with asymmetric context.<n>We derive supervision online from tutor consensus by sampling multiple document-grounded reasoning traces.
  arXiv  Detail & Related papers  (2026-02-24T05:56:20Z)
• Conservative Bias in Multi-Teacher Learning: Why Agents Prefer Low-Reward Advisors [0.0]
  This paper reveals an unexpected phenomenon in interactive reinforcement learning (IRL)<n>When given a choice between teachers with different reward structures, learning agents overwhelmingly prefer conservative, low-reward teachers.
  arXiv  Detail & Related papers  (2025-12-19T02:38:04Z)
• BD at BEA 2025 Shared Task: MPNet Ensembles for Pedagogical Mistake Identification and Localization in AI Tutor Responses [0.7475784495279183]
  We present our submission to the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors.<n>Our system is built on MPNet, a Transformer-based language model that combines BERT and XLNet's pre-training advantages.<n>Our approach achieved strong results on both tracks, with exact-match macro-F1 scores of approximately 0.7110 for Mistake Identification and 0.5543 for Mistake Location on the official test set.
  arXiv  Detail & Related papers  (2025-06-02T15:57:49Z)
• J1: Incentivizing Thinking in LLM-as-a-Judge via Reinforcement Learning [54.85131761693927]
  We introduce J1, a reinforcement learning framework for teaching LLM judges to think before making decisions.<n>Our core contribution lies in converting all judgment tasks for non-verifiable and verifiable prompts into a unified format with verifiable rewards.<n>We then use RL to train thinking-judges at scales of 8B, 32B, and 70B and show that they obtain state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-05-15T14:05:15Z)
• Learning to Love Edge Cases in Formative Math Assessment: Using the AMMORE Dataset and Chain-of-Thought Prompting to Improve Grading Accuracy [0.0]
  This paper introduces AMMORE, a new dataset of 53,000 math open-response question-answer pairs from Rori. We conduct two experiments to evaluate the use of large language models (LLM) for grading challenging student answers.
  arXiv  Detail & Related papers  (2024-09-26T14:51:40Z)
• Unbiased Teacher for Semi-Supervised Object Detection [50.0087227400306]
  We revisit the Semi-Supervised Object Detection (SS-OD) and identify the pseudo-labeling bias issue in SS-OD. We introduce Unbiased Teacher, a simple yet effective approach that jointly trains a student and a gradually progressing teacher in a mutually-beneficial manner.
  arXiv  Detail & Related papers  (2021-02-18T17:02:57Z)

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.