RL for Language Model Reasoning

GRPO-style reinforcement learning (RL)-based LLM fine-tuning algorithms have recently gained popularity. Relying on heuristic trust-region approximations, however, they can lead to brittle optimization behavior, as global importance-ratio clipping and group-wise normalization fail to regulate samples whose importance ratios fall outside the clipping range. We propose Query-Adaptive Trust-Region policy Optimization (QUATRO), which directly enforces trust-region constraints through a principled optimization. This yields a clear and interpretable objective that enables explicit control over policy updates and stable, entropy-controlled optimization, with a stabilizer terms arising intrinsically from the exact trust-region formulation. Empirically verified on diverse mathematical reasoning benchmarks, QUATRO shows stable training under increased policy staleness and aggressive learning rates, maintaining well-controlled entropy throughout training.

Agentic Reinforcement Learning (ARL) trains large language models to interleave reasoning with external tool execution to solve complex tasks. Most existing ARL methods train a single set of parameters to support both reasoning and tool-use behaviors, implicitly assuming that joint training leads to improved overall agent performance. Despite its widespread adoption, this assumption has rarely been examined empirically. In this paper, we systematically examine this assumption by introducing Capability Effect Attribution (CEA), which provides quantitative evidence of interference between reasoning and tool-use behaviors. Through an in-depth analysis, we show that these two capabilities often induce misaligned gradient directions, leading to training interference that undermines the effectiveness of joint optimization and challenges the prevailing ARL paradigm. To address this issue, we propose Disentangled Action--Reasoning Tuning (DART), a simple and efficient framework that explicitly decouples parameter updates for reasoning and tool use via separate low-rank adaptation modules. With this simple change alone, DART outperforms all joint-optimization baselines and approaches the 2-Agent upper bound across thirteen benchmarks on retrieval-augmented QA and NL2SQL, further supporting our finding of capability interference under shared optimization.

Reinforcement learning (RL) has become a key driver of language model reasoning. Among RL algorithms, Group Relative Policy Optimization (GRPO) is the de facto standard, avoiding the need for a critic by using per-prompt baselines and variance normalization. Yet why and when this normalization helps remains unclear. In this work, we answer both questions through the lens of local curvature of the sequence-level policy gradient: standard deviation normalization implements an adaptive gradient. Theoretically, we prove that under mild conditions GRPO attains an improved convergence rate over unnormalized REINFORCE, with gains characterized by the average within-prompt reward standard deviation across prompts and iterations. We further introduce IS-GRPO, an importance-sampling variant of GRPO whose expected update remains aligned with the full gradient, and prove a convergence guarantee of the same form as REINFORCE's, which is tighter in practice during real training runs by a factor we measure. Empirically, on GSM8K and MATH we validate the curvature--variance link and measure the quantities that govern our bounds along real training runs. At 1.5B scale, per-prompt normalization outperforms both unnormalized and globally normalized baselines, with gains that emerge in a middle phase of training where per-prompt variances become heterogeneous. At 7B scale, the normalization schemes become statistically indistinguishable while IS-GRPO retains a small lead, in line with the theory's prediction that the gains require heterogeneity.

Long chain-of-thought reasoning (Long CoT) is now fundamental to state-of-the-art LLMs, especially in mathematical reasoning. However, LLM generation is highly sequential, and long CoTs lead to a high latency. We propose to train Divide-and-Conquer CoT (DC-CoT) to reduce the latency. With DC-CoT, the model can act as a director that identifies distinct subtasks that can be performed in parallel in its reasoning process, and then spawns workers to execute the subtasks. Our goal is to achieve high accuracy, with a low longest path length, which is a theoretical measure of the latency needed for the response. We start with a long CoT base model (DeepScaleR-1.5B-Preview), and first use SFT with a small curated demonstration set to initialize its ability to spawn workers in a certain format. Because SFT degrades the accuracy significantly, we design a multi-stage RL algorithm, with various data filtering strategies, to recover the accuracy while decreasing the longest path length. Across several benchmarks including AIME 2024 and HMMT 2025, DC-CoT achieves similar accuracy as DeepScaleR-1.5B-Preview while decreasing longest path length by 35-40%. Our code, SFT dataset and models are publicly available at https://github.com/amahankali10/DC_CoT_RL_for_Low_Latency_CoT_with_Parallel_Reasoning.

RLVR has become a standard recipe for training LLMs on reasoning tasks with verifiable outcomes, but when rollout generation dominates the cost, efficiency hinges on which prompts are sampled and when. In practice, prompt pools are often static or only weakly coupled to policy progress, so uniform sampling fails to track the moving capability frontier and wastes rollouts on regions that are already solved or still unreachable. Prior methods improve efficiency via filtering, curricula, adaptive rollout allocation, or teacher guidance, but they often assume a fixed pool, which does not support stable on-policy pool growth, or they introduce additional teacher cost and latency. In this work, we propose HeaPA (Heap Sampling and On-Policy Query Augmentation), which maintains a bounded, evolving pool, tracks the frontier with heap-based boundary sampling, grows the pool via on-policy augmentation under lightweight asynchronous validation, and stabilizes correlated queries via topology-aware pool statistics re-estimation and controlled reinsertion. Across two training corpora, two training recipes, and seven benchmarks, HeaPA consistently improves accuracy and reaches target performance with fewer computations at comparable wall-clock time. Analyses attribute the gains to frontier-focused sampling and on-policy pool growth, with more pronounced improvements at mid-to-large model scales. Our training code is publicly available at https://github.com/horizon-llm/HeaPA.

On-policy reinforcement learning (RL) for language model post-training suffers from a fundamental tension: as training progresses, policy entropy collapses and sampling diversity diminishes, causing the model to ``forget'' its own earlier exploratory capacity. While off-policy data can restore diversity, existing methods mix entire trajectories at the sequence level, introducing severe policy mismatch and training instability. We argue that the core question is not \emph{whether} to use off-policy data, but \emph{where} in the sequence it should appear. Based on this insight, we propose \textbf{Thinking Seeds}, a token-level mix-policy framework that uses the model's own historical checkpoints as off-policy prefixes, providing diverse starting points for reasoning, while the critical continuation is generated on-policy to preserve gradient quality. Through token-level importance ratios, Thinking Seeds effectively leverages historical diversity without compromising training stability. Extensive experiments across models and mathematical reasoning benchmarks demonstrate that Thinking Seeds consistently outperforms standard on-policy training and existing off-policy extensions. Our analysis reveals that the method maintains higher effective entropy, reduces gradient loss from clipping, and expands the explorable solution space, clarifying how position-aware mix-policy modeling improves both exploration and final performance in LLM RL.

Large language models (LLMs) struggle with complex, long-horizon reasoning due to instability caused by their frozen policy assumption. Current test-time scaling methods treat execution feedback merely as an external signal for filtering or rewriting trajectories, without internalizing it to improve the underlying reasoning strategy. Inspired by Popper's epistemology of "conjectures and refutations," we argue that intelligence requires real-time evolution of the model's policy through learning from failed attempts. We introduce Policy of Thoughts (PoT), a framework that recasts reasoning as a within-instance online optimization process. PoT first generates diverse candidate solutions via an efficient exploration mechanism, then uses Group Relative Policy Optimization (GRPO) to update a transient LoRA adapter based on execution feedback. This closed-loop design enables dynamic, instance-specific refinement of the model's reasoning priors. Experiments show that PoT dramatically boosts performance: a 4B model achieves 49.71% accuracy on LiveCodeBench, outperforming GPT-4o and DeepSeek-V3 despite being over 50 smaller.

RL methods for scaling large reasoning models stall on datasets with low initial success rates, and thus little training signal. We investigate a fundamental question: Can a pretrained LLM leverage latent knowledge to generate an automated curriculum for problems it cannot solve? We explore this with SOAR: An asymmetric self-play framework that uses meta-RL to surface these pedagogical signals. A teacher model proposes synthetic problems for a student model, and is rewarded with its improvement on a subset of hard problems, thus grounding the curriculum in real student progress rather than intrinsic proxy rewards. Our study on the hardest subsets of math benchmarks (0/128 success) reveals three core findings. First, it is possible to realize bilevel meta-RL that unlocks learning under sparse, binary rewards by sharpening a latent capacity of pretrained models to generate useful problems. Second, grounded rewards outperform intrinsic learnability rewards used in prior LLM self-play, reliably avoiding typical instability and diversity collapse modes. Third, the structure and well-posedness of questions are more critical for learning progress than solution correctness. Our results suggest that the ability to generate useful stepping stones does not require the preexisting ability to solve the hard problems, paving a principled path to escape reasoning plateaus without additional curated data

RL-trained Lean theorem provers mode-collapse at inference time: on miniF2F-test with DeepSeek-Prover-V1.5-RL, doubling the i.i.d.\ sampling budget from $k{=}32$ to $k{=}64$ produces zero additional solved theorems (42/244 in both cases). A fixed schedule of 15 tactic skeletons breaks this plateau and recovers a $+45$ relative improvement at $k{=}16$ (mean $Δ= +12.3 \pm 4.2$ theorems across $n{=}3$ seeds, sign preserved in every seed). A controlled diversity ablation rules out the prompt-diversity confound: tactic skeletons help, paraphrases match the baseline, and irrelevant Lean comments actively degrade. A leave-one-out formalization-difficulty stratification reveals a structural-content gradient across the three perturbations. The phenomenon is RL-specific: V1.5-Base proves zero theorems regardless of intervention, identifying RL as the stage that creates the proof capability which subsequently collapses; extending to two additional 7B Lean provers, RL-trained DeepSeek-Prover-V2-7B contributes $+3$ frontier solves no i.i.d. baseline can reach despite a flat aggregate, while SFT-trained Goedel-Prover does not ( $-10.0$ $\pm 4.4$ theorems, $n{=}3$, sign preserved every seed). Inference-time structural diversity is a cheap, complementary axis for RL-trained provers, orthogonal to scaling model size or training compute.

Agentic Reinforcement Learning (RL) has empowered Large Language Models (LLMs) to utilize tools like Python interpreters for complex problem-solving. However, for parameter-constrained models (e.g., 4B--7B), the exploration phase is often plagued by frequent execution failures, creating noisy trajectories that hinder policy optimization. Under standard outcome-based reward settings, this noise leads to a critical credit assignment issue, where erroneous actions are inadvertently reinforced alongside successful outcomes. Existing mitigations face a dilemma: dense rewards often trigger reward hacking, while supersampling incurs prohibitive computational costs. To address these challenges, we propose CLEANER. Distinct from external filtering methods, CLEANER exploits the model's intrinsic self-correction capabilities to eliminate error-contaminated context directly during data collection. At its core, the Similarity-Aware Adaptive Rollback (SAAR) mechanism autonomously constructs clean, purified trajectories by retrospectively replacing failures with successful self-corrections. Based on semantic similarity, SAAR adaptively regulates replacement granularity from shallow execution repairs to deep reasoning substitutions. By training on these self-purified paths, the model internalizes correct reasoning patterns rather than error-recovery loops. Empirical results on AIME24/25, GPQA, and LiveCodeBench show average accuracy gains of 6%, 3%, and 5% over baselines. Notably, CLEANER matches state-of-the-art performance using only one-third of the training steps, highlighting trajectory purification as a scalable solution for efficient agentic RL. Our models and code are available at GitHub

Existing reinforcement learning methods for LLM reasoning implicitly assume that the policy generating training trajectories should coincide with the one producing inference responses. We argue that this is a misleading inductive bias: the optimization-optimal trajectory distribution favors informative gradients, whereas the inference-optimal response distribution emphasizes accuracy and consistency. Forcing both into a single policy entangles their gradients and suppresses exploration. We propose R$^2$PO (Residual Rollout Policy Optimization), which attaches a lightweight Residual Rollout-Head atop the policy to decouple training trajectories from inference responses, diversifying rollouts during training while keeping inference generation intact. Experiments show that R$^2$PO consistently outperforms baselines, with average accuracy gains of 3.4% on MATH-500 and 1.3% on APPS, alongside more diverse rollouts and reduced length bias. Our code is available at https://github.com/RRPO-ARR/Code.

Reinforcement Learning with Verifiable Rewards (RLVR) is highly effective for enhancing LLM reasoning, yet recent evidence shows models like Qwen 2.5 achieve significant gains even with spurious or incorrect rewards. We investigate this phenomenon and identify a "Perplexity Paradox": spurious RLVR triggers a divergence where answer-token perplexity drops while prompt-side coherence degrades, suggesting the model is bypassing reasoning in favor of memorization. Using Path Patching, Logit Lens, JSD analysis, and Neural Differential Equations, we uncover a hidden Anchor-Adapter circuit that facilitates this shortcut. We localize a Functional Anchor in the middle layers (L18-20) that triggers the retrieval of memorized solutions, followed by Structural Adapters in later layers (L21+) that transform representations to accommodate the shortcut signal. Finally, we demonstrate that scaling specific MLP keys within this circuit allows for bidirectional causal steering-artificially amplifying or suppressing contamination-driven performance. Our results provide a mechanistic roadmap for identifying and mitigating data contamination in RLVR-tuned models. Code is available at https://github.com/idwts/How-RLVR-Activates-Memorization-Shortcuts.

Training reliable tool-augmented agents remains a significant challenge, largely due to the difficulty of credit assignment in multi-step reasoning. While process-level reward models offer a promising direction, existing LLM-based judges often produce noisy and inconsistent signals because they lack fine-grained, task-specific rubrics to distinguish high-level planning from low-level execution. In this work, we introduce SCRIBE (Skill-Conditioned Reward with Intermediate Behavioral Evaluation), a reinforcement learning framework that intervenes at a novel mid-level abstraction. SCRIBE grounds reward modeling in a curated library of skill prototypes, transforming open-ended LLM evaluation into a constrained verification problem. By routing each subgoal to a corresponding prototype, the reward model is equipped with precise, structured rubrics that substantially reduce reward variance. Experimental results show that SCRIBE achieves state-of-the-art performance across a range of reasoning and tool-use benchmarks. In particular, it improves the AIME25 accuracy of a Qwen3-4B model from 43.3% to 63.3%, and significantly increases success rates in complex multi-turn tool interactions. Further analysis of training dynamics reveals a co-evolution across abstraction levels, where mastery of mid-level skills consistently precedes the emergence of effective high-level planning behaviors. Finally, we demonstrate that SCRIBE is additive to low-level tool optimizations, providing a scalable and complementary pathway toward more autonomous and reliable tool-using agents.

Knowledge Base Question Answering (KBQA) challenges models to bridge the gap between natural language and strict knowledge graph schemas by generating executable logical forms. While Large Language Models (LLMs) have advanced this field, current approaches often struggle with a dichotomy of failure: they either generate hallucinated queries without verifying schema existence or exhibit rigid, template-based reasoning that mimics synthesized traces without true comprehension of the environment. To address these limitations, we present \textbf{KBQA-R1}, a framework that shifts the paradigm from text imitation to interaction optimization via Reinforcement Learning. Treating KBQA as a multi-turn decision process, our model learns to navigate the knowledge base using a list of actions, leveraging Group Relative Policy Optimization (GRPO) to refine its strategies based on concrete execution feedback rather than static supervision. Furthermore, we introduce \textbf{Referenced Rejection Sampling (RRS)}, a data synthesis method that resolves cold-start challenges by strictly aligning reasoning traces with ground-truth action sequences. Extensive experiments on WebQSP, GrailQA, and GraphQuestions demonstrate that KBQA-R1 achieves state-of-the-art performance, effectively grounding LLM reasoning in verifiable execution.

Language models frequently produce plausible yet incorrect reasoning traces that are difficult to verify. We investigate fine-tuning models to use Prolog as an external symbolic reasoning tool, training Qwen2.5-3B-Instruct with Group Relative Policy Optimization (GRPO) on a cleaned version of GSM8K (which we release as gsm8k-prolog-prover). We systematically vary prompt structure, reward composition (execution, syntax, semantics, structure), and inference protocol (single-try, multiple-try, and two agentic modes). Our reinforcement learning approach outperforms supervised fine-tuning on GSM8K, and the resulting 3B model achieves zero-shot performance on MMLU-STEM and MMLU-Pro competitive with 7B few-shot baselines. Most importantly, we identify an accuracy--auditability trade-off: configurations tuned for correctness alone learn to delegate reasoning to natural language and use Prolog only for the final computation, while configurations rewarded for symbolic structure produce fully auditable programs at a cost in accuracy. We interpret this trade-off as a form of reward hacking and discuss its implications for deploying neurosymbolic systems in safety-critical domains. The source code for our experiments is available under https://github.com/aisilab/Prolog-as-a-Tool

Reinforcement learning (RL) algorithms such as PPO and GRPO are widely used to train large language models (LLMs) for multi-turn agentic tasks. However, in off-policy training pipelines, these methods can exhibit unstable optimization dynamics and are prone to perfor- mance collapse. Through empirical analysis, we identify two fundamental sources of instability in this setting: (1) a granularity mismatch between token-level policy optimization and turn- structured interactions, and (2) high-variance and unreliable gradient updates induced by off- policy importance sampling and inaccurate advantage estimation. To address these challenges, we propose SORL, Stabilizing Off-Policy Reinforcement Learning for Long-Horizon Agent Train- ing. SORL introduces mechanisms that align policy optimization with the structure of multi- turn interactions and adaptively suppress unreliable off-policy updates, yielding more conserva- tive and robust learning dynamics. Within this framework, we instantiate two stabilized algo- rithms: SO-PPO and SO-GRPO. Both algorithms are designed to mitigate gradient variance and prevent optimization collapse without requiring careful early stopping or heuristic tuning. We evaluate SO-PPO and SO-GRPO on benchmarks spanning open-domain QA, multi-hop QA, and medical multiple-choice QA, and further assess their transfer to asynchronous RL for mathe- matical reasoning by training on DAPO-Math-17k and validating on AIME-2024. These results demonstrate that SORL provides a practical, scalable, and general framework for stabilizing re- inforcement learning in multi-turn LLM agent training and asynchronous RL for mathematical reasoning.

Scaling inference-time computation has enabled Large Language Models (LLMs) to achieve strong reasoning performance, but their inherently sequential decoding incurs substantial latency, motivating parallelization of the generation process. However, existing parallel reasoning approaches suffer from performance degradation compared to their sequential counterparts, and often rely on specialized inference engines. We introduce ThreadWeaver, a framework for adaptive parallel reasoning that matches the accuracy of comparably sized sequential reasoning models while significantly reducing inference latency via three key innovations: 1) a two-stage parallel trajectory generator that produces high-quality parallel chain-of-thought data for supervised fine-tuning; 2) a trie-based rollout design that enables parallel reasoning on any off-the-shelf autoregressive inference engine; and 3) a parallelization-aware reinforcement learning framework that trains the model to balance reasoning accuracy with effective parallelization. Across six challenging math reasoning benchmarks, ThreadWeaver trained on top of Qwen3-8B achieves performance on par with cutting-edge sequential reasoning models (79.9% on AIME24 and 71.9% on average) while delivering up to 1.53x speedup in token latency, establishing a new Pareto frontier between accuracy and efficiency.

Reinforcement learning (RL) is often credited with improving language model reasoning at the expense of knowledge. We challenge this narrative by showing that reasoning models consistently outperform their instruction-tuned versions on pure knowledge recall tasks. These gains do not reflect newly acquired information, but rather an improved procedural skill in navigating and searching existing knowledge hierarchies within the model parameters. Structured prompting, which explicitly guides models through hierarchical traversal -- recovers most of the instruct-reasoning gap across five model families. A controlled RL experiment on unseen, non-extractable facts improves recall of held-out frequent but previously inaccessible facts, ruling out simple data exposure. On depth-stratified retrieval tasks, reasoning models exhibit superior traversal as retrieval depth grows. Layerwise activation analysis further shows that while factual representations maintain high cosine similarity between instruct and reasoning models, query representations diverge noticeably, indicating that reasoning primarily reshapes how models traverse knowledge rather than the knowledge representation itself. Finally, we find that distilled models often fail to match reasoning models on knowledge recall because they imitate self-correction without acquiring the exploratory behavior needed for hierarchical navigation. Together, these findings suggest that improving factual recall in LLMs depends not only on expanding what models know but also on teaching them to navigate it -- motivating future post-training methods that optimize traversal.

Recent advances in large language model (LLM) reasoning through reinforcement learning rely on annotated datasets for verifiable rewards, which may limit models' ability to surpass human-level performance. While self-play offers a promising alternative, prior methods yield only marginal or even negative gains on post-trained models because they generate problems that cluster around familiar concepts rather than discovering novel ones. We introduce Open-Ended Self-Improving Reasoner (OpenSIR), a self-play framework in which a single LLM alternates teacher and student roles to generate and solve novel problems without external verifiers or annotated data. Starting from a single seed problem, OpenSIR sustains open-ended exploration through diversity rewards that push the model toward unfamiliar concepts and difficulty calibration that keeps problems learnable. Across seven math benchmarks, OpenSIR consistently improves all models, averaging +3.6 points on instruction models and +3.1 on reasoning models, while recent self-play baselines yield marginal or even negative gains; starting from a single trivial seed, it also surpasses GRPO baselines trained on over 7K annotated examples. Despite training only on self-generated math, OpenSIR is the only self-play method that transfers to general reasoning, improving by at least +4.4 points on reasoning models.

Large reasoning models (LRMs) often consume excessive tokens, inflating computational cost and latency. More broadly, in goal reaching sequential decision problems we often want to reach the goal quickly, and LRM reasoning can be viewed through this lens. We challenge the assumption that longer responses improve accuracy. By penalizing reasoning tokens using a discounted reinforcement learning setup (interpretable as a small token cost) and analyzing Blackwell optimality in restricted policy classes, we encourage concise yet accurate reasoning, analogous to preferring shorter successful trajectories in a stochastic shortest path problem. Experiments confirm our theoretical results that this approach shortens chains of thought while preserving accuracy.

Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model. In this paper, we investigate the value of deliberate exploration -- explicitly incentivizing the model to discover novel and diverse behaviors -- and aim to understand how the knowledge in pre-trained models can guide this search. Our main finding is that exploration with a simple, principled, representation-based bonus derived from the pre-trained language model's hidden states significantly improves diversity and pass@k rates -- both for post-training, and in a novel inference-time scaling setting we introduce. For inference-time, exploration with representation-based diversity improves efficiency, consistently improving pass@k rates across a variety of models and reasoning tasks. For example, for Qwen-2.5-14b-Instruct we obtain over 50% improvement in verifier efficiency on almost all tasks. For post-training, we show that integrating this exploration strategy into an RL pipeline improves reasoning performance over that of the initial model and over standard RL post-training. For example, on AIME 2024, our post-trained Qwen-2.5-7b-Instruct's pass@80 matches the pass@256 of GRPO on the same model, demonstrating a 3x improvement in test-time sample efficiency. Overall, our findings suggest that deliberate exploration -- with the right notion of diversity -- is a practical path toward discovery of new behaviors beyond sharpening.

Reinforcement Learning (RL) has become a key driver for enhancing the long chain-of-thought (CoT) reasoning capabilities of Large Language Models (LLMs). However, prevalent methods like GRPO often fail when task difficulty exceeds model capacity, leading to reward sparsity and inefficient training. Prior work attempts to mitigate this with off-policy data, but such methods often induce severe distributional mismatches that destabilize policy updates. In this work, we identify a core issue underlying these failures, which we term low training affinity, and introduce Affinity, the first quantitative metric for monitoring the compatibility between external guidance and the model's intrinsic policy. To address this, we propose HINT, an adaptive framework designed to enhance reasoning capabilities while explicitly preserving high Affinity. First, instead of revealing partial answers, HINT supplies Meta-Hints, which act as abstract cognitive scaffolding to guide the model in articulating solutions independently. Second, to ensure stability, we integrate Affinity-Aware Policy Optimization (AAPO), which dynamically modulates the learning objective based on the Affinity. Extensive experiments across diverse benchmarks demonstrate that HINT consistently outperforms strong baselines, while exhibiting superior stability and robust generalization to out-of-distribution tasks. Code is available at https://github.com/ViviqwerAsd/HINT.

Training expert LLMs in domains with scarce data is difficult, often relying on multiple-choice questions (MCQs). However, standard outcome-based reinforcement learning (RL) on MCQs is risky. While it may improve accuracy, we observe it often degrades reasoning quality such as logical consistency. Existing solutions to supervise reasoning, such as large-scale Process Reward Models (PRMs), are prohibitively expensive. To address this, we propose CLARity, a cost-effective RL framework that enhances reasoning quality using only a small, general-purpose LLM. CLARity integrates a consistency-aware reward mechanism with a 2-stage refine-then-monitor training pipeline to enhance reasoning consistency, and a dynamic data reformulation strategy to to better exploit limited data. Experiments demonstrate that CLARity improves response consistency by 16.5% and accuracy by 7.5% over baselines. Human evaluations further confirm holistic improvements in coherence and professionalism. Thus, CLARity offers a generalizable solution that enables smaller models to effectively guide expert models by reasoning consistency. Our code is open sourced at: https://github.com/Infinite-set/CLARity

Diffusion large language models (dLLMs) are promising alternatives to autoregressive large language models (AR-LLMs), as they potentially allow higher inference throughput. Reinforcement learning (RL) is crucial to enabling dLLMs to achieve performance comparable to that of AR-LLMs on important tasks, such as reasoning. However, RL algorithms well-suited to dLLMs' unique characteristics have yet to be developed. This paper proposes Distribution Matching Policy Optimization (DMPO), a principled and theoretically grounded RL fine-tuning method specifically designed to enhance the reasoning capabilities of dLLMs by matching the dLLM policy distribution to the optimal, reward-tilted one through cross-entropy optimization. We identify a key implementation challenge with small training batch sizes and propose several effective solutions based on a novel weight baseline subtraction technique. DMPO exhibits superior performance on multiple reasoning benchmarks without supervised fine-tuning, achieving up to a $39.63$ percentage-point improvement in accuracy over prior non-DMPO RL baselines and $67.97$ percentage points over the base model, underscoring the effectiveness of the distribution-matching framework. Our code is available at https://github.com/yuchen-zhu-zyc/DMPO.

What do thinking language models learn during training that their base models lack? We first present an unsupervised method that discovers a model's reasoning behaviors by training small Sparse Autoencoders on sentence-level activations of reasoning traces, yielding interpretable reasoning taxonomies. Building on this, we introduce constructive model diffing, which aims to reconstruct the base-to-fine-tuned difference from interpretable components: reasoning mechanisms (category vectors that can induce a reasoning behavior in the base model) and reasoning heuristics (a classifier determining when a mechanism should fire). Across nine base/thinking pairs (four RL-trained, four SFT-distilled, one mixed), two independent findings agree: category vectors in the base model converge to far lower loss for taxonomies derived from purely RL-trained models, and hybrid models recover roughly 76% of the RL base-to-thinking gap but only 11% of the SFT gap. This indicates RL primarily teaches heuristics for orchestrating pre-existing base mechanisms, whereas SFT-distillation installs new ones, offering a new lens on what training paradigms teach, with implications for efficient reasoning-model development.

Reinforcement Learning with Verifiable Rewards (RLVR) has become a widely adopted technique for enhancing the reasoning ability of Large Language Models (LLMs). However, the effectiveness of RLVR strongly depends on the capability of base models. This issue arises because it requires the model to have sufficient capability to perform high-quality exploration, which involves both effectiveness and diversity. Unfortunately, existing methods address this issue by imitating expert trajectories, which improve effectiveness but neglect diversity. To address this, we argue that the expert only needs to provide guidance only at critical decision points rather than the entire reasoning path. Based on this insight, we propose MENTOR: Mixed-policy Expert Navigation for Token-level Optimization of Reasoning, a framework that provides expert guidance only at critical decision points to perform effective and diverse exploration in RLVR. Extensive experiments show that MENTOR enables models capture the essence of expert strategies rather than surface imitation, thereby performing high-quality exploration and achieving superior overall performance. Our code is available online.

Recent thinking models are capable of solving complex reasoning tasks by scaling test-time compute, but this scaling should be allocated in line with task difficulty. On one hand, short reasoning (underthinking) leads to errors on harder problems that require extended reasoning steps; but, excessively long reasoning (overthinking) can be token-inefficient by generating unnecessary steps even after reaching a correct intermediate solution. We refer to this as under-adaptivity, where the model fails to modulate its response length appropriately given problems of varying difficulty. To address under-adaptivity and strike a balance between under- and overthinking, we propose TRAAC (Think Right with Adaptive, Attentive Compression), an online post-training RL method that leverages the model's self-attention to identify key steps and prune redundant ones. TRAAC also estimates difficulty and incorporates it into training rewards, thereby learning to allocate a reasoning budget commensurate with example difficulty. Across a variety of tasks (AIME, AMC, GPQA-D, BBEH), TRAAC (Qwen3-4B) achieves an average absolute accuracy gain of 8.4% with a relative reduction in reasoning length of 36.8% compared to the base model, and a 7.9% accuracy gain paired with a 29.4% length drop compared to the best RL baseline. TRAAC generalizes well, with accuracy and efficiency gains on out-of-distribution non-math datasets like GPQA-D, BBEH, and OptimalThinkingBench. Our analysis shows that TRAAC learns to adjust its thinking budget based on difficulty and that a combination of task-difficulty calibration and attention-based compression yields gains across diverse tasks.

Reinforcement Learning with Verifiable Rewards (RLVR) replaces costly human labeling with automated verifiers. To reduce verifier hacking, many RLVR systems binarize rewards to $\{0,1\}$, but imperfect verifiers inevitably introduce \emph{false negatives} (rejecting correct answers) and \emph{false positives} (accepting incorrect ones). We formalize verifier unreliability as a stochastic reward channel with asymmetric noise rates $ρ_0$ and $ρ_1$ -- the FP rate and the FN rate, respectively. From this abstraction we derive two lightweight corrections: (i) a \emph{backward} correction that yields an unbiased surrogate reward and thus an unbiased policy-gradient estimator in expectation, and (ii) a \emph{forward} correction that reweights score-function terms so the expected update aligns with the clean gradient direction and requires only the FN rate. We implement both as lightweight hooks in a group relative policy optimization pipeline, both corrections improve RLVR for math reasoning under synthetic and real verifier noise, with the forward variant being more stable under heavier noise. Finally, an appeals mechanism with a lightweight LLM verifier estimates the FN rate online and further improves performance.

Existing multi-agent learning approaches have developed interactive training environments to explicitly promote collaboration among multiple Large Language Models (LLMs), thereby constructing stronger multi-agent systems (MAS). However, during inference, they require re-executing the MAS to obtain final solutions, which diverges from human cognition that individuals can enhance their reasoning capabilities through interactions with others and resolve questions independently in the future. To investigate whether multi-agent interaction can enhance LLMs' independent problem-solving ability, we introduce ILR, a novel co-learning framework for MAS that integrates two key components: Dynamic Interaction and Perception Calibration. Specifically, Dynamic Interaction first adaptively selects either cooperative or competitive strategies depending on question difficulty and model ability. LLMs then exchange information through Idea3, an innovative interaction paradigm designed to mimic human discussion, before deriving their respective final answers. In Perception Calibration, ILR employs Group Relative Policy Optimization (GRPO) to train LLMs while integrating one LLM's reward distribution characteristics into another's reward function, thereby enhancing the cohesion of multi-agent interactions. We evaluate the effectiveness of ILR across three LLMs from two model families of varying scales on five mathematical, one coding, one general question answering, and one scientific reasoning benchmarks. Experimental results show that ILR consistently outperforms single-agent learning, yielding an improvement of up to 5% over the strongest baseline. We further discover that Idea3 can enhance the robustness of stronger LLMs during multi-agent inference, and dynamic interaction types can boost multi-agent learning compared to pure cooperative or competitive strategies.

Recent advancements have endowed Large Language Models with impressive general reasoning capabilities. However, these reasoning models often perform worse than non-reasoning models on personalization tasks. While some methods use outcome-based RL to improve personalization reasoning, they fail to supervise the reasoning process. As a result, models may reach correct answers through flawed reasoning chains, limiting further improvement. To address this, we propose TagPR, a novel framework that adds semantic tags to the reasoning process for step-by-step guidance. TagPR first automatically generates a structured, tagged dataset for Supervised Fine-Tuning. It then employs a multi-stage RL process guided by a composite reward signal, which integrates tag-based process supervision with a novel Personalization Reward Model with User Embeddings to achieve fine-grained alignment with user-specific logic. Extensive experiments on public LaMP, LongLaMP, PGraphRAG, and a self-constructed dataset demonstrate that our approach achieves state-of-the-art results, delivering an average improvement of 32.65% over the base model across all LaMP benchmark tasks. Our work demonstrates that tag-guided process supervision is an effective approach for personalization reasoning.