TraceForge introduces a two‑stage training method that generates reasoning traces in the style of a target model family, using supervised learning followed by adversarial refinement. The system produces traces that are judged as authentic with scores comparable to real traces, and when applied to teacher answers, it improves performance on coding benchmarks such as HumanEval+ and MBPP+. The approach addresses the limitation of existing models that only return answers without detailed reasoning, enabling more transparent and learnable outputs.
By Yan Wang
arXiv:2608. 08503v1 Announce Type: new Abstract: Mathematical reasoning remains challenging in low-resource languages such as Bangla.
By Rahma Simin Ali, Jawad Hossain
The paper introduces Residual Advantage (RA), a new guidance method for reinforcement learning with verifiable rewards (RLVR) that treats the teacher–student probability residual as a bounded one‑step reward, subtracts the student’s state value to form an advantage, and centers it within each response. RA preserves the verifier’s mean label while redistributing credit among response steps, and its extension CoRA updates the teacher model using verifier advantages to adapt guidance to the student’s attempts. Experiments with Qwen3 models show that RA combined with GRPO or REINFORCE++ consistently outperforms teacher‑only on‑policy distillation across three mathematical benchmarks, improving macro Avg@8 and Pass@8 scores, with CoRA providing additional gains.
By Xiaobing Chen, Zhiqi Pang
The paper introduces a recursive self-improvement framework for language models that replaces an external teacher with a frozen copy of the student, enabling dynamic co-evolution (DCE) and self-refined concise learning (SRCL). DCE allows the privileged teacher to evolve alongside the student, while SRCL trains on shorter, verified rewrites to reduce verbosity. Experiments show that the combined DCE+SRCL approach outperforms traditional on‑policy self‑distillation across multiple model sizes and math benchmarks, achieving significant accuracy gains and shorter outputs.
By Shangjian Yin, Zehao Zhao, Kavosh Asadi, Rui Liu, Yuchen Lu, Shike Mei, Hang Cui, Luke Simon, Zhouxing Shi, Hamed Firooz
Mathematical reasoning remains challenging in low-resource languages such as Bangla. We study whether teacher-generated Bangla Chain-of-Thought (CoT) supervision provides benefits beyond ordinary supervised fine-tuning.
arXiv:2607. 05734v1 Announce Type: cross Abstract: Chain-of-thought (CoT) distillation in the recommendation domain is a necessary precursor to RL training, but raw teacher traces are ill-suited to this task.
By Haz Sameen Shahgir, Yufei Li, Frank Shyu, Luke Simon, Sandeep Pandey, Xi Liu, Yue Dong
arXiv:2607. 25182v1 Announce Type: cross Abstract: The ability to retrieve relevant tables for answering questions is a key task for structured information retrieval.
By Adarsh Singh, Kushal Raj Bhandari, Jianxi Gao, Soham Dan, Vivek Gupta
arXiv:2607. 22629v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) produce long, explicit chains of intermediate steps before generating a final answer at inference time.
By Durgesh Kalwar, Vardhan Palod, Subbarao Kambhampati
arXiv:2607. 08255v1 Announce Type: new Abstract: Large language models increasingly serve as teachers generating training data for smaller students.
By Miseong Shawn Kim
The paper introduces Verifier-Gated Multi-Expert On-Policy Distillation (VG‑OPD), a method that assigns teacher supervision at the token level based on each expert’s counterfactual gain on a specific answer criterion. VG‑OPD localizes supervision where experts disagree most with the student and weights it by criterion importance, integrating this into a gated KL advantage for reinforcement learning. Applied to scientific reasoning, VG‑OPD achieves top performance on seven benchmarks for 4B and 8B models, outperforming prior multi‑teacher distillation approaches.
By Xun Xu, Zaixi Zhang
arXiv:2608. 04794v1 Announce Type: new Abstract: Self-distillation (SD) has emerged as a compute-efficient alternative to reinforcement learning with verifiable rewards: a self-teacher, conditioned on privileged information (PI) about the answer such as a reference solution, supplies dense per-token supervision to a student that never sees it.
By Sarthak Harne, Chinmay Karkar, Yash Pandya, Ahmed Awadallah, Akshay Nambi
arXiv:2607. 02234v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) has emerged as a promising paradigm for improving LLM reasoning, where a privileged teacher with access to reference solutions provides token-level supervision on the student's own generated trajectories.
By Zhanming Shen, Jintao Tong, Shaotian Yan, Chen Shen, Hao Chen, Wentao Ye, Xiaomeng Hu, Rui Miao, Haobo Wang, Junbo Zhao, Gang Chen, Jieping Ye