Entropy-Cut Metropolis-Hastings: Sampling-Based Reasoning Without RL Training
This paper introduces Entropy-Cut Metropolis-Hastings (ECMH), an algorithm that samples from a 'power distribution' over base language model outputs to elicit strong reasoning without reinforcement learning posttraining. Rather than cutting reasoning traces at uniformly random positions, ECMH uses next-token entropy as a proxy to identify consequential decision points (e.g., choice of proof strategy), then resamples from those positions. The authors prove that mixing time scales with the number of decisions rather than tokens, and demonstrate consistent improvements over RL-trained models on MATH500, HumanEval, GPQA Diamond, and AIME26.
Related guides (4)
Related events (8)
ExpRL: RL-based mid-training using human QA data as reward scaffolds for LLM reasoning
ExpRL proposes an automated approach to LLM mid-training that replaces manually curated reasoning traces with large corpora of human-written QA data used as reward scaffolds rather than imitation targets. Reference solutions are hidden from the policy and used only to construct problem-specific grading rubrics, enabling dense process-level rewards that reinforce partial progress and intermediate reasoning steps. On challenging math reasoning benchmarks, ExpRL outperforms SFT, sparse-reward GRPO, and self-distillation as an RL initialization strategy, with additional mixed-domain experiments suggesting broader applicability.
Equilibrium Reasoners: Learning Attractors Enables Scalable Reasoning
This paper introduces Equilibrium Reasoners (EqR), a framework that formalizes test-time compute scaling through learned task-conditioned attractors in latent space, where stable fixed points correspond to valid solutions. EqR scales along two axes—depth (more iterations) and breadth (aggregating stochastic trajectories)—without requiring external verifiers or task-specific priors. On Sudoku-Extreme, unrolling up to 40,000 equivalent layers boosts accuracy from 2.6% (feedforward baseline) to over 99%. The work provides a mechanistic lens for understanding why iterative latent models generalize beyond memorized patterns.
Reasoning in Memory (RiM): Latent Reasoning via Working Memory Blocks in LLMs
RiM introduces a latent reasoning method that replaces autoregressive chain-of-thought token generation with fixed sequences of special 'memory block' tokens, allowing LLMs to perform internal computation without externalizing intermediate steps. These memory blocks are processed in a single forward pass rather than generated autoregressively, improving compute efficiency at test time. Training uses a two-stage curriculum: first grounding memory blocks by predicting explicit reasoning steps, then discarding step-level supervision and refining answers iteratively. Experiments across multiple model families and sizes show RiM matches or exceeds existing latent reasoning methods.
Semi-supervised framework scales LLM reasoning with minimal labeled data via lightweight verifier
A new arXiv preprint proposes a semi-supervised framework for training LLMs to reason with very few labeled examples, using a lightweight classifier to judge the validity of intermediate reasoning traces. An entropy-based confidence threshold filters unreliable pseudo-labels before fine-tuning. Experiments on math reasoning (Orca-Math subset) and visual QA (GQA) show accuracy comparable to using 10-15x more labeled data. The approach reduces dependence on expensive answer-level supervision by turning verification into a data-creation mechanism.
VEPO: Vision-anchored token selection improves RL for visual reasoning
A new arXiv paper identifies a failure mode of entropy-based credit assignment in multimodal reinforcement learning: vision-sensitive tokens with naturally low entropy are systematically ignored, causing the mechanism to collapse in visual reasoning tasks. The authors propose VEPO (Vision-Entropy token-selection for Policy Optimization), which couples visual sensitivity with token entropy via a multiplicative scheme to redirect gradient credit toward tokens that are both visually grounded and semantically informative. VEPO outperforms entropy-only baselines by 2.28 points at 7B scale and 3.15 points at 3B scale on visual reasoning benchmarks.
STARE: Token-level advantage reweighting to prevent entropy collapse in GRPO-style RL training
Researchers introduce STARE, a method addressing policy entropy collapse in GRPO-style reinforcement learning from verifiable rewards (RLVR) for LLM post-training. Through first-order gradient analysis, they identify a token-level credit assignment mismatch and propose selectively reweighting advantages for entropy-critical tokens using batch-internal surprisal quantiles plus a closed-loop entropy gate. Evaluated across 1.5B–32B models on short/long chain-of-thought and multi-turn tool use tasks, STARE outperforms DAPO and other baselines by 4–8% on AIME24/25 while sustaining stable training over thousands of steps.
RREDCoT: Segment-level reward redistribution for chain-of-thought reasoning via self-approximated credit assignment
RREDCoT is a new method for redistributing rewards across segments of Chain-of-Thought traces during RL fine-tuning of reasoning language models, addressing the high-variance delayed-reward problem inherent in GRPO-style training. Rather than using computationally expensive Monte Carlo sampling for intermediate state value estimation, the method uses the model itself to approximate optimal reward redistribution without additional generation passes. The paper evaluates RREDCoT against MC sampling and several attribution baselines, analyzing segmentation strategies and state value estimation. This is relevant to the active research thread on improving RL fine-tuning stability and efficiency for reasoning models.
OneReason: Activating Chain-of-Thought Reasoning in Generative Recommendation Models
Researchers from the OneRec team introduce OneReason, a framework for enabling reasoning capabilities in generative recommendation models deployed across short-video, live-streaming, advertising, and e-commerce. The work identifies a key failure mode — that naive thinking-mode integration does not outperform non-thinking baselines — and diagnoses this as a deficit in two factors: itemic token perception and user behavior cognition. The proposed solution combines perception-focused pre-training, a three-level cognition-enhanced CoT format for supervised fine-tuning, and a specialize-then-unify RL training recipe.