arXiv AI September 25, 2026 By Ruochen Jiao, Besnik Fetahu, Zhenyu Shi, Priyanka Nigam

CounterRoute: Self-Routed Reasoning via Hierarchical Counterfactual Credit Assignment

CounterRoute is an online reinforcement‑learning framework that jointly learns how to route a language model’s reasoning between a ‘think’ and a ‘direct answer’ mode, using a single shared policy derived from a dual‑mode checkpoint. It employs counterfactual rollouts to credit routing decisions and a curriculum that starts with forced dual‑mode rollouts before shifting to self‑routed updates, achieving better accuracy‑efficiency trade‑offs across nine benchmarks. The method reduces generated tokens by up to 51% on Qwen3‑8B while improving macro‑average accuracy, and its routing strategy generalizes to unseen coding, science, and commonsense tasks.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Aug 3

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute

arXiv:2607. 28457v1 Announce Type: cross Abstract: Scaling test-time computation can improve language-model reasoning, but uniform budgets waste computation on easy inputs, while verifier-guided refinement relies on external feedback.

By Hongyu Chen, Liang Lin, Guangrun Wang

reinforcement-learning benchmarks

arXiv AI

Jun 30

DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer Training

arXiv:2606. 30345v1 Announce Type: cross Abstract: Enabling large language models to achieve stable self-improvement without external expert supervision remains a central challenge in complex reasoning tasks.

By Haisen Luo, Yiwei Liu, Haoning Wang, Dan Liu, Junxi Yin, Haotian Wang, Lei Zhang, Xiaoyu Tian, Shuaiting Chen, Yuansheng Song, Baoyan Guo, Xiongfei Yan, Bolan Yang, Chengwei Liu, Ming Cui, Jiong Chen

llms reinforcement-learning efficiency benchmarks

arXiv AI

Sep 16

Post-Training Large Language Models via Reinforcement Learning from Self-Feedback

arXiv:2507.21931v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) often produce plausible but poorly-calibrated answers, limiting their reliability on reasoning-intensive tasks....

By Carel van Niekerk, Renato Vukovic, Benjamin Ruppik, Hsien-chin Lin, Shutong Feng, Milica Ga\v{s}i\'c

llms nlp reinforcement-learning fine-tuning

arXiv AI

Aug 14

Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents

arXiv:2608. 12764v1 Announce Type: cross Abstract: Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per trajectory, which is far too sparse for effective credit assignment.

By Haoze Wu, Chuqiao Kuang, Tianyi Zhuang, Xiaoguang Li

agents reinforcement-learning efficiency

arXiv AI

Aug 5

Agentic Reinforcement Learning with Self-Distilled Reward Shaping

arXiv:2608. 03223v1 Announce Type: cross Abstract: Agentic reinforcement learning enables LLM agents to learn through interaction, but sparse trajectory-level rewards reveal success without identifying which intermediate decisions deserve credit.

By Ranxu Zhang, Guinan Chen, Chenshaodong, Jinghao Lin, Xiaozhou Xu, Sunzhe, Yanyong Zhang, Chao Wang

llms agents reinforcement-learning benchmarks

arXiv AI

4d ago

SIPO: Unifying Reinforcement Learning with On-Policy Self-Distillation

SIPO (Self‑Instructing Policy Optimization) unifies reinforcement learning with on‑policy self‑distillation by using a contrastive self‑teacher to generate token‑level credit signals. The method samples multiple rollouts per prompt, pairs each with a reference answer and its mistakes, and uses the difference in teacher log‑probabilities to provide dense feedback while still respecting the overall task reward. Experiments on reasoning and code‑generation benchmarks show that SIPO outperforms both RLVR and OPSD baselines without requiring an external teacher or extra generation steps.

By Zhenrui Yue, Huimin Zeng, Yueqi Wang, Yaokun Liu, Fengran Mo, Jinghan Zhang, Mung Yao Jia, Gyuseok Lee, Yang Zhang, Na Wei, Dong Wang

llms reinforcement-learning efficiency benchmarks

One email a morning, machine-written

Related stories

SVR: Self-Verifying Refinement via Joint Verdict-Confidence Reinforcement Learning for Adaptive Test-Time Compute

DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer Training

Post-Training Large Language Models via Reinforcement Learning from Self-Feedback

Beyond Outcome Rewards: Step-Level Self-Distilled Policy Optimization for Deep Search Agents

Agentic Reinforcement Learning with Self-Distilled Reward Shaping

SIPO: Unifying Reinforcement Learning with On-Policy Self-Distillation