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.
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.
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.
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....
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.
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.
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.
The paper introduces temporal self‑distillation for reinforcement learning with verifiable rewards (RLVR), proposing that a policy can learn from a stronger future checkpoint of itself. Two methods—Near‑Future Policy Optimization (NPO) and Near‑Future Policy Distillation (NPD)—use verified future‑self trajectories and token‑level transfer, respectively, while AutoNPO adaptively selects the optimal future checkpoint. Experiments on eight image‑text benchmarks show that near‑future teachers yield higher performance than far‑future ones, indicating that the balance between new capability and learner compatibility is key.
arXiv:2609. 03241v1 Announce Type: cross Abstract: A reasoning model can improve from its own on-policy experience, but this inner loop is fragile: terminal verifiers provide reliable yet sparse supervision, while dense same-model guidance can reinforce false confidence or overconcentrate learning on a narrow solution mode.
arXiv:2511.05933v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) is often credited with improving reasoning at the expense of factual knowledge. We instead find that reasoning mo...
arXiv:2606. 17803v1 Announce Type: new Abstract: Large language models achieve strong reasoning performance by scaling inference-time compute, yet remain fundamentally stateless, discarding the rich, self-produced reasoning traces generated during this process.
The paper demonstrates that fine‑tuning reasoning models to predict their own confidence at intermediate steps—using only 600 self‑supervised examples—substantially improves inference efficiency. Without adding any explicit stopping or length penalties, the models generate up to 25 % fewer tokens while maintaining accuracy on mathematical, scientific, and coding benchmarks across several architectures. The study finds that confidence supervision preserves the models’ high‑level reasoning structure rather than merely suppressing specific behaviors.
arXiv:2607. 10966v1 Announce Type: new Abstract: We introduce Self-Verified Reasoner (SVR-R1), a multi-turn RL framework that turns a model's own verification into a learning signal for multimodal reasoning.