The paper presents a cost‑effective approach for industrial explainable‑recommendation systems by decoupling explanation generation from selection. Candidate explanations are pre‑generated using six prompt styles and two commodity LLMs, then a lightweight CPU‑resident selector (e.g., LambdaRank) chooses the best one at request time, achieving sub‑100 ms latency without GPUs. Experiments on a 2,958‑pair Google Local subset and a 300‑pair MovieLens‑1M split show that pairwise ranking methods outperform single‑action RL baselines, while KG‑path selectors achieve near‑perfect user satisfaction scores.
By Tanay Chowdhury, Saeideh Shahrokh Esfahani
The paper introduces VANE, a new routing strategy for Mixture-of-LoRA-experts that scores experts based on the expected loss reduction of their updates rather than token similarity. By decomposing each expert into a reader and writer, VANE evaluates all reader–writer pairs using a low‑rank compass that predicts the descent direction, enabling efficient top‑k selection with additive gates. Experiments on Llama‑3 models show VANE outperforms twelve PEFT and MoE‑LoRA baselines while using fewer trainable parameters and providing router scores that better reflect expert usefulness.
By Priya Nair, Lukas Brenner, Maya Lindqvist, Daniel Whitmore, Wen-Hsuan Liu, Tom Saliencro, Amara Okonkwo, Rohan Desai
OptiSelect is a framework that incorporates the optimizer’s effect into online data selection for large language model pretraining. The study shows that optimizers like Lion and Muon, which use sign-based or polar-tangential preconditioners, suffer from a discriminability collapse that limits selection gains, whereas diagonal‑adaptive optimizers such as AdamW and Sophia can achieve higher gains. Experiments on 124M and 720M models confirm the theory and demonstrate that OptiSelect remains effective even when data is rephrased.
By Simin Fan, Alireza Abdollahpoorrostam, Martin Jaggi
arXiv:2609.39687v1 Announce Type: new
Abstract: On-policy self-distillation (OPSD) trains mathematical reasoning models using a privileged teacher that sees a reference solution and supervises studen...
By Xincheng Wei, Yifan Ding, Yoshua Li, Yuquan Lu, Ziheng Li, Yi Lu, Dongsheng Ma, Rongxiang Weng, Xunliang Cai
The paper presents a cost‑effective approach for industrial explainable‑recommendation systems by decoupling explanation generation from selection. Explanations are pre‑generated using six prompt styles and two commodity LLMs, then a lightweight CPU‑resident selector (e.g., LambdaRank) chooses the best one at request time, achieving sub‑100 ms latency without GPUs. Experiments on a 2,958‑pair Google Local subset and a 300‑pair MovieLens‑1M split show that pairwise ranking outperforms single‑action RL methods, while KG‑path selectors achieve near‑perfect unique‑output rates, and the overall end‑to‑end build cost is around $15 on commodity hardware.
arXiv:2606. 25178v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has been extended from single-domain training to multi-domain reasoning suites spanning mathematics, programming, and science.
By Yongjin Yang, Jiarui Liu, Yinghui He, Lechen Zhang, Bernhard Sch\"olkopf, Zhijing Jin
arXiv:2608. 03316v1 Announce Type: new Abstract: On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language: identical VAE latents, matching architectures, and a common timestep grid.
By Siming Fu, Zheming Fu, Ruizhe He, Hualiang Wang, Jie Huang, Xiaoxiao Ma, Mingchen Zhong, Weihu Huang, Xiaoxuan He, Haojun Xu
arXiv:2608.21811v1 Announce Type: new
Abstract: Reinforcement learning for vision-language math reasoning starves under sparse reward: on a pool of 20,830 visual-math problems where Qwen2-VL-2B answe...
By Qiqian Fu
arXiv:2608.21501v1 Announce Type: new
Abstract: Credit assignment in large-language-model reinforcement learning (LLM RL) can be separated into three objects: evidence about success, a transport oper...
By Qifan Shi, Zhaolu Kang, Chenghua Zhu
arXiv:2606. 29476v1 Announce Type: cross Abstract: Self-distilled agentic reinforcement learning augments trajectory-level reward with a token-level distillation loss, using as its teacher the same policy conditioned on privileged context.
By Zibin Meng, Kani Chen
On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language: identical VAE latents, matching architectures, and a common timestep grid. We ask what happens when none of this holds, as when the strongest teacher available and the student one wishes to deploy come from different model families, and find that the standard recipes have no answer: teacher latents cannot serve as targets in a foreign coordinate system, per-pixel losses against a teacher that stochastically re-draws local detail degenerate into blur or divergence, and timestep indices lose their meaning across mismatched schedules.
arXiv:2606. 23740v1 Announce Type: cross Abstract: Offline reinforcement-learning losses (RFT, RIFT, DFT, Offline GRPO, DPO) are widely used to distill reasoning from large teachers into smaller students, and are typically compared on downstream accuracy alone.
By Aleksandr Nikolich, Igor Kiselev, Vladimir Platonov, Karina Romanova