RL Fine-Tuning

In many modern applications of reinforcement learning (RL), the natural reward for a task of interest is inherently sparse: a reward of 0 is given everywhere except when the task is completed, when a reward of +1 is given. Training a policy to maximize such a sparse reward requires solving a challenging credit assignment problem, leading to slow or ineffective RL improvement. We propose a simple approach to transform a sparse outcome reward into a dense process reward. Our approach relies on training a discriminator to distinguish between previous successful and unsuccessful episodes, and using this discriminator to incentivize the RL-learned policy to match the state-action visitations of successful episodes, while avoiding those of unsuccessful episodes. By incentivizing the policy to match the visitations over all states, not just those that correspond to task success, this reward provides dense feedback on whether progress is being made towards task completion, and, we show, provably achieves this without changing the optimal policy. Focusing on finetuning of robotic control policies, we demonstrate that our approach leads to significantly faster RL finetuning performance on both simulated and real-world manipulation tasks, as compared to simply maximizing the sparse outcome reward.

Existing Reinforcement Learning (RL) research for Text-to-Speech (TTS) focuses on large language models (LLMs), leaving Flow-Matching (FM) under-explored. We present FlowTTS-GRPO, an online RL framework for FM-based TTS. By converting ordinary differential equation (ODE) trajectories into stochastic differential equation (SDE) paths, our method enables direct fine-tuning of open-source FM models without auxiliary models. We show that a weighted reward combination converges faster than a probabilistic scheme, and identify three practical optimizations: omitting classifier-free guidance (CFG) during training accelerates convergence; synthesizing hard cases improves robustness; and applying RL to the FM component enhances audio-detail metrics. Experiments on CosyVoice 3.0 and F5-TTS demonstrate objective and subjective preference gains in speaker similarity and perceptual quality, with F5-TTS also improving intelligibility.

Recent advances in large language models (LLMs) have demonstrated that reinforcement fine-tuning of pretrained base models can lead to significant gains in reasoning performance at inference time. In this work, we theoretically analyze why reinforcement fine-tuning induces better reasoning ability than purely supervised fine-tuning (SFT) methods. We model chain-of-thought (CoT) reasoning as a pathfinding problem on graphs and compare the popular method of reinforcement learning with verifiable rewards (RLVR) against traditional SFT. We prove that SFT, when trained on golden shortest paths without negative examples, fails to learn how to efficiently backtrack. In contrast, an RLVR-trained model can learn how to efficiently backtrack from dead ends using only outcome reward. This leads to an exponential separation in inference-time compute between the two methods, and demonstrates that RLVR leads the model to learn the location of difficult decisions in a reasoning chain, ultimately allowing for better allocation of inference-time compute. Finally, we show that the reasoning traces of an RLVR model can be distilled to train a base model to backtrack efficiently as well.

Recent advancements in generative imitation learning have significantly propelled the field of robotic manipulation. However, the majority of existing models rely heavily on Behavior Cloning (BC), a paradigm that suffers from compounding errors and distributional shift. Consequently, the efficacy of these models in practical industrial deployments remains limited. To address these challenges, we introduce a novel, plug-and-play fine-tuning pipeline designed to facilitate the robust deployment of Vision-Language-Action (VLA) models in real-world environments. In contrast to contemporary reinforcement learning (RL) fine-tuning strategies, which are often constrained by specific model architectures, our proposed framework is model-agnostic and adaptable to a diverse range of VLA models. We conceptualize VLA-generated actions as a unified interface, upon which we train a residual policy. This policy is designed to rectify suboptimal actions and address the distributional shift inherent in imitation learning. Additionally, we incorporate human-in-the-loop guidance to ensure safe exploration and maximize training efficiency. We conduct experiments directly in real-world robotic settings. The results demonstrate that within only 1.5 hour of real-world online RL training, the average success rate exceeds 95% on real robots. Our work presents a practical solution for deploying behavior cloning models in industrial scenarios.

A natural recipe for intelligent robotic decision-making is initializing from pretrained generative control policies, which have summarized offline experience, and adapting them to self-collected online experience. We present DF-ExpEnse, an exploration technique that improves the quality of online experience collection, thus increasing finetuning sample-efficiency. DF-ExpEnse leverages the multimodal modeling capabilities of the generative control policy to create an expressive and tractably evaluatable candidate set. It then utilizes an ensemble of critics to identify the action that best balances quality with high exploration interest. In fleet settings, DF-ExpEnse further enables cross-agent communication to facilitate collaborative exploration as a group. DF-ExpEnse can be seamlessly integrated with existing strategies that finetune pretrained generative control policies via reinforcement learning. We experimentally validate consistent sample-efficiency benefits through DF-ExpEnse across a variety of manipulation and locomotion tasks, compared to default finetuning and alternative action selection schemes. Project can be found at https://df-expense.github.io.

Long-context reasoning is an essential capability for large language models, particularly when they are deployed as autonomous agents that must reason over lengthy trajectories. Reinforcement learning (RL) has recently emerged as a dominant paradigm for improving this ability, yet existing work largely focuses on reward engineering while diverse training data remains scarce. We revisit this problem from a data-centric perspective and show that a simple yet effective data recipe alone, paired with a minimal outcome-based GRPO setup, suffices to substantially improve long-context reasoning. Our recipe targets three complementary task families -- retrieval, multi-evidence synthesis, and reasoning -- for which we construct and curate eight datasets totaling ~14K examples. Experiments on three models (Qwen3-4B/8B/30B-A3B) yield average gains of +7.2/+3.2/+6.4 points across seven long-context benchmarks, surpassing prior RL training sets. We further demonstrate that these gains transfer to agentic tasks, where continuing RL training on an agent-tuned model with our data recipe improves GAIA by +4.8 and BrowseComp by +7.0 points. We will release our datasets to facilitate future research.

When pretrained VLA policies are fine-tuned through online RL, each rollout episode produces only a single binary outcome (success or failure), yet the actor update requires per-transition supervision. Existing approaches commonly reduce this sparse outcome to a single scalar reward or advantage signal, which conflates distinct forms of transition-level feedback and provides limited guidance once basic task success becomes achievable. First, a single scalar signal conflates the two objectives of viability and efficiency; once basic success is achieved, the binary label provides no gradient to distinguish efficient completions from slow ones. Second, real-world rollouts mix autonomous and intervention segments; naively assigning episode outcomes across these boundaries introduces incorrect credit assignment. To address these issues, we propose Hierarchical Advantage-Weighted Behavior Cloning (HABC), which trains separate critic heads for these two objectives on different data subsets and combines their outputs with a state-adaptive balance. A state-adaptive gate $g_t$ merges their one-step advantages, prioritizing viability when success is uncertain and shifting to efficiency only when viability is high, and converts the result into per-transition weights on the actor loss. Intervention-aware credit assignment further restricts outcome labels to segments executed by the current policy, preventing supervision from leaking across intervention boundaries. In real-robot experiments on three contact-rich bimanual tasks, HABC raises success from supervised fine-tuning (SFT) baselines of 36%, 44%, and 12% to 92%, 88%, and 38%.

We use Group Relative Policy Optimization (GRPO), a recently devised sample and memory efficient reinforcement learning method, to finetune pretrained LLMs in the range of 1.5B to 14B parameters equipped with the ability to get current information through the use of a Wikipedia revisions tool, or news summaries, to forecast real events beyond the knowledge cutoff of the LLM, as well as problems made to simulate different aspects of the dynamics of that training. We use the results of these experiments to comment on the scaling capability of LLMs for forecasting, as well as classify how judgmental forecasting fits into the verifiable/unverifiable domain taxonomy, considering the impact of the inherent aleatoric uncertainty when forecasting future events (e.g. the roll of a die). As a result of the GRPO training, we manage to bring a 1.5B parameter transformer (Qwen 2.5 1.5B) to forecasting performance superior to Claude Sonnet 3.5 over the same dataset as measured by cross entropy from the market agreed probabilities. We also discuss various dead ends on the path to this result.

Optimization modeling is inherently hierarchical, requiring a precise sequence of symbolic commitments. Traditional learning-based automated optimization modeling methods improve modeling policies through large-scale annotated or curated training data, but are costly to adapt to new problem distributions. Meanwhile, one-shot generation remains brittle in hierarchical modeling, where early symbolic errors can propagate into invalid formulations. Test-time scaling offers a promising alternative by enabling structural exploration with additional instance-level computation; however, existing search-based methods typically rely on a fixed policy, causing repeated rollouts to inherit similar modeling biases and providing limited credit assignment for intermediate decisions. To address these limitations, we propose StarOR, a synergistic search-and-adaptation framework that couples MCTS with Test-Time Reinforcement Learning for optimization modeling. StarOR decomposes the modeling process into four stages and updates a transient LoRA adapter via GRPO at each non-terminal node. By using MCTS-generated siblings as local comparison sets, StarOR transforms search-time exploration into instance-specific policy refinement. Moreover, an unsupervised multi-faceted reward system provides fine-grained feedback for intermediate formulation decisions without ground-truth labels. Experiments across five optimization benchmarks show that StarOR achieves state-of-the-art performance even with a 4B backbone, outperforming existing methods and the frontier LLMs.

The rapid progress of reasoning and agentic large language models (LLMs) has increased the demand for long-context inference, but self-attention (SA) scales quadratically with context length. To address this, we study SWARR (Sliding-Window Attention with Reinforced Adaptation for Math Reasoning), a practical recipe for adapting SWA models to mathematical reasoning. SWARR has two stages: (1) efficient conversion from a pretrained SA model to SWA with supervised fine-tuning (SFT), which avoids pretraining a new base model, and (2) policy adaptation with reinforcement learning (RL). We find that SWA still underperforms SA after SFT, and we hypothesize that this gap is caused in part by a data-architecture mismatch: most SFT data are prepared for SA models and may contain long-range dependencies that are difficult for SWA to model. Because on-policy RL optimizes self-generated trajectories under the SWA constraint, it can adapt trajectories to better match SWA. Experiments on mathematical reasoning benchmarks show that this recipe substantially narrows the gap between SWA and SA, recovering much of the accuracy lost during SWA conversion while preserving the efficiency benefits of linear-complexity attention. Our central contribution is the empirical finding that RL changes the conclusion one would draw from conversion and SFT alone about SWA's viability for math reasoning.

Graphical User Interfaces (GUIs) serve as the dominant medium for human-computer interaction, yet building GUI agents that generalize across the vast diversity of real-world interface environments, with the same flexibility and robustness that humans naturally exhibit, remains unsolved. Notably, GUI data are inherently non-stationary: the continual emergence of previously unseen interface instances (e.g., novel domains and resolutions) induces persistent distribution shifts, significantly impeding the continual learning of existing GUI agents. Reinforcement fine-tuning (RFT) has attracted considerable attention as a promising approach. Nevertheless, RFT exhibits pronounced instability in its grounding capability, manifested as sharp reward discontinuities and high-variance oscillations. The imbalanced distribution of rollout outcomes introduces substantial noise into advantage estimation, leading to policy overconfidence. The fixed clipping bound suppresses the increase in policy probabilities needed to adapt to new distributions, leading to a collapse in exploration capacity. To address these challenges, we propose GUI-AC, a method that enhances the continual learning capability of GUI agents. GUI-AC introduces grounding certainty to support two core mechanisms: (i) Adaptive Advantage, which down-weights noisy advantage estimates to prevent policy overconfidence; and (ii) Dynamic Clipping, which relaxes the clipping bound to encourage exploration range. Extensive experiments show that these mechanisms jointly improve performance, enabling our method to surpass state-of-the-art baselines. Code is available anonymously at https://github.com/Can-Lin/GUI-AC.

During instruction fine-tuning (IFT), large language models (LLMs) learn to follow instructions by using the provided context to answer a query. While prior work has studied how context characteristics correlate with context usage by the LLM, this analysis has been limited to inference time, leaving open how these relationships are acquired in the first place. Here, we measure how models' sensitivity to such characteristics shifts across successive IFT stages: supervised fine-tuning (SFT), direct preference optimization (DPO), and reinforcement learning with verifiable rewards (RLVR). Experiments across four models and three datasets show that SFT makes models more likely to use contexts that are easy to understand, such as containing high length, context-query similarity, and fluency. Post-SFT dynamics may either reinforce or resolve these preferences depending on the training dataset. Our findings reveal that context usage is actively reshaped at each IFT stage, and designing a balanced IFT dataset is important in ensuring robust context utilization of instruction-tuned models.

Theory of Mind (ToM) is a must-acquire skill for modern foundation model systems to operate effectively and safely in the real world. Recent works have explored honing ToM via post-training; however, we show that such progress is confounded by a pervasive "shortcut" issue: tasks can reach up to 99% accuracy by simply exploiting spurious causal correlations, leading to a false sense of ToM. Motivated by this, we first develop a framework to systematically examine ToM datasets for shortcuts and provide guidance for future development. We find that questions reducible to pure state tracking, such as "belief," are especially shortcut-prone compared to mind questions, such as "intention," where reasoning beyond tracking is required. Using four shortcut-free datasets across three ToM contexts, we then comprehensively study whether Reinforcement Fine-Tuning with verifiable rewards and explicit reasoning chains, called Thinking-RFT, elevates ToM beyond Supervised Fine-Tuning, or SFT. Our key findings are as follows. First, Thinking-RFT effectively improves ToM in all scenarios, with a 6% improvement over SFT, particularly in complex higher-order reasoning, with a 10% improvement over SFT, and multimodal cases, with a 7% improvement over SFT. It also generalizes notably better to unseen domains and higher-order queries while being more robust to counterfactuals. Second, ToM benefits specifically from the joint effect of reasoning and RL: Thinking-RFT outperforms Non-Thinking-RFT by 7% on average. Third, RFT works by learning to ground its reasoning on anchor cues, such as keywords and state changes, that correspond to causal factors. We believe our study is useful for developing effective and robust ToM post-training datasets and advancing critical ToM capabilities.

We present an online reinforcement learning (RL) algorithm for fine-tuning flow-matching policies in continuous-control problems. Our key insight is to view RL-based policy improvement as a transport of action densities towards regions of high reward, which naturally aligns with the transport formulation of flow matching models. Prior methods either approximate the current or optimal policy distribution or resort to distillation, which introduces biased gradients or sacrifices multimodal modeling capacity. In contrast, our approach for RL with Density Transport, which we name \emph{RLDT}, constructs a transport field from a maximum-entropy RL objective using Stein Variational Gradient Descent (SVGD). Then, it finetunes a pretrained flow matching policy to align with this field. Training with this alignment objective is nontrivial because flow-matching policies generate actions via a multi-step process, making direct gradient-based optimization challenging. To overcome this challenge and stabilize training, we approximate policy actions from intermediate denoising steps via expected-target estimation. This allows the transport-field update to propagate into the network parameters without unstable backpropagation through time. Experimental results demonstrate that RLDT outperforms competitive baselines in reward quality and convergence speed. This performance holds across diverse continuous-control tasks, encompassing both dense and sparse rewards, as well as state- and vision-based long-horizon robot manipulation. The project webpage is https://rpfey.github.io/rldt/.

Recent advancements in reasoning language models have been driven by Reinforcement Learning (RL) fine-tuning. Most often, these rely on the Group Relative Policy Optimization (GRPO) algorithm or modifications thereof to steer the models to produce Chain-of-Thought (CoT) traces. The final answer can only be verified, and the reward assigned, after the CoT trace is complete, making it a delayed reward problem. GRPO and its modifications correspond to Monte Carlo methods in standard RL, which are known to suffer from high variance. A possible solution to this problem is the redistribution of rewards through credit assignment, where segments of the CoT trace that are important for arriving at the desirable solution are emphasized by assigning a higher reward. While Monte Carlo sampling can be used to provide an unbiased estimate of intermediate state values, its computational overhead makes it unsuitable for train-time credit assignment in long contexts at high granularity. We introduce RREDCoT (Reward REDistribution for Chain of Thoughts), which utilizes the model itself to approximate the optimal reward redistribution without additional generation. We investigate the advantages of our method compared to MC sampling and several attribution methods. We further analyze several aspects relevant to the construction of the redistribution such as segmentation of CoT traces and state value estimation.

Latent reasoning has emerged as a promising alternative to discrete Chain-of-Thought (CoT) in large language models (LLMs), enabling more expressive reasoning by operating over continuous representations. However, the inherently deterministic nature of continuous representations limits policy exploration in reinforcement learning (RL). To address this, we propose TARPO (Token-Wise Latent-Explicit Reasoning via Action-Routing Policy Optimization), a pure RL framework that adaptively switches between discrete token generation and continuous latent reasoning at each step. TARPO introduces a lightweight action head router that observes the current hidden state and samples a routing decision from a binary mode-selection space, preserving the stochasticity of discrete token sampling from the vocabulary. The LLM backbone and router are jointly optimized end-to-end with a shared group-relative advantage signal. Extensive experiments across Qwen2.5 (from 1.5B to 7B) and Llama-3.1-8B backbones demonstrate that TARPO consistently outperforms existing explicit and latent reasoning RL baselines across diverse benchmarks. Further analysis shows that TARPO learns adaptive token-wise switching behaviors while maintaining stable training dynamics. Our code is available at https://github.com/NKU-LITI/TARPO-master.

Post-training Vision-Language-Action (VLA) models into policies that can be reliably deployed on real robots remains a major bottleneck. SFT and DAgger exploit failure signals only indirectly, and reward-based RL is bottlenecked by the difficulty of real-world reward design and of training reliable critics. We present FlowPRO, a reward-free offline reinforced fine-tuning framework for flow-matching VLAs. Algorithmically, we propose RPRO (Robotic Flow-matching Proximalized Preference Optimization), a preference-optimization objective tailored to the flow-matching action head of VLA models. RPRO pairs a contrastive optimizer with an explicit proximal regularizer that anchors the absolute magnitude of the implicit reward, thereby eliminating the reward-hacking failure mode of plain Flow-DPO. On the data side, a teleoperated intervention-and-rollback paradigm produces naturally paired positive and negative trajectories $(τ^w, τ^l)$ on a real robot from a single operator action; a Smooth Interpolation procedure, combined with batch mixing, then converts these sparse corrections into dense per-state supervision while preserving the base policy's capabilities. On four long-horizon bimanual tasks, FlowPRO attains the highest success rate, outperforming four representative baselines, and ablations confirm the contribution of each loss component.

Multi-modal Large Language Models (MLLMs) have demonstrated remarkable capabilities in semantic understanding and common sense reasoning, making them promising candidates for solving planning problems in autonomous driving. However, the next-token text prediction objectives traditionally used in pre-training and supervised fine-tuning (SFT) of MLLMs may fall short of fulfilling the planning objectives for autonomous vehicles. The next-token prediction objective merely encourages per-token imitation in text, often irrespective of multi-step consequences and the alignment with crucial planning considerations such as giving space to other road actors. To overcome these limitations, we propose a reinforcement learning fine-tuning (RLFT) approach, MAGNIFIED, that aligns the MLLM-based driving agent with planning objectives by learning from token-level rewards. By mapping a sequence of predicted tokens to corresponding vehicle trajectories and learning from planning rewards, MAGNIFIED optimizes for the true planning objectives rather than focusing solely on token prediction accuracy, enabling the model to refine its understanding of the planning task beyond simple imitation. We validate our approach on the Waymo Open Motion Dataset with a novel setup incorporating rasterized birds-eye views and tokenized trajectories as inputs and planning-oriented outputs. An initial SFT phase establishes a strong baseline in outputting plan trajectories as sequences of X-Y coordinates in text, while subsequent RL fine-tuning substantially enhances planning performance relative to the SFT baseline (demonstrating over a 10.5% reduction in overlap rate and a 38.9% reduction in off-road rate), underscoring the potential of RLFT on MLLMs to achieve vehicle planning that is better aligned with compliant, comfortable, and efficient driving.

Vision-Language-Action (VLA) models offer a promising end-to-end paradigm for unmanned aerial vehicles (UAVs) to accomplish complex tasks specified by fine-grained instructions. However, standard supervised fine-tuning (SFT) suffers from data scarcity, limited generalization, and weak supervision for nuanced and complicated human intents. Reinforcement fine-tuning offers a natural way to mitigate these challenges and align policy behaviors with human intents through designable feedback, but applying it to aerial navigation remains challenging due to inefficient exploration in expansive continuous spaces. To address these challenges, we introduce an efficient reinforcement learning (RL) framework for VLA-based aerial navigation. At its core, we propose EG-GRPO (Expert-Guided Group Relative Policy Optimization) to augment online rollouts with few-shot expert data. Additionally, we design a heterogeneous pipeline enabling parallel simulation and inference, which reduces rollout time by 43.5%. Across multiple tasks specified by complex human intents, EG-GRPO improves the success rate to 2.13x that of the SFT baseline, while improving intent alignment performance by 60.9%. These results demonstrate that our framework can move aerial navigation toward precise intent-aligned flight.

Distilling expert demonstration data into large generative models using behavioral cloning is a scalable approach to learning capable policies for robotic control, particularly for dexterous manipulation. Reinforcement learning (RL) can be used as a means to finetune these policies further using additional experience. An open question is whether RL is more sample-efficient than collecting more human demonstrations. Prior work has finetuned large pretrained policies in a scalable fashion by applying RL to a smaller residual policy that corrects the pretrained model. However, for the typical sparse reward tasks, RL algorithms can struggle to optimize the behavior in a sample-efficient manner. We explore inverse reinforcement learning, where a dense reward function is learned from expert demonstrations, potentially reducing the challenge of RL finetuning. We specifically consider coherent imitation learning, an IRL method that facilitates improvement of the BC policy through using a specific reward formulation with theoretical guarantees. We show that our IRL method maintains or improves the performance of pi-0.5 on all six sparse manipulation tasks and achieves a $\geq 90\%$ success rate on five out of six complex manipulation tasks, outperforming RL-based baselines using sparse rewards. By ensuring our initial pretrained finetuning policy is optimal for our initial reward and critic, our method circumvents the initial drop commonly seen in RL finetuning and enables faster improvement.

Large language models are increasingly deployed in multi-turn interactive settings where users or environments can iteratively provide lightweight feedback. Unfortunately, optimizing such behavior presents a sharp dilemma in practice: online reinforcement learning is able to effectively address multi-turn dynamics but is prohibitively expensive due to the cost of generating full correction trajectories at every update, whereas offline supervised fine-tuning (SFT) is efficient but suffers from distribution shift and behavioral collapse. To this end, we novelly propose DRIFT (Decoupled Rollouts and Importance-Weighted Fine-Tuning), a framework that operationalizes the theoretical insight that the KL-regularized RL objective is equivalent to importance-weighted supervised learning. DRIFT decouples rollout from optimization by sampling offline interaction trajectories from a fixed reference policy, deriving return-based importance weights, and optimizing the policy via weighted SFT on the resulting dataset. Empirically, we demonstrate that DRIFT matches or exceeds the performance of multi-turn reinforcement learning baselines while maintaining the training efficiency and simplicity of standard supervised fine-tuning. Code is available at https://github.com/2020-qqtcg/DRIFT.

Reinforcement Learning (RL) has become pivotal for improving model capabilities yet suffers from rollout efficiency bottlenecks due to the long-tail response length distribution. While existing works mitigate the impact of long tails via prompt-level tail scheduling, we focus on the root source of inefficiency: the distribution itself. Specifically, we characterize the long-tail distribution at a finer granularity, identifying intra-prompt long tails, and revealing that they frequently consist of ineffective verbosity. To address this, we propose a novel paradigm of active distribution shaping to shape the rollout distribution towards conciseness and certainty, thereby fundamentally resolving tail-induced overheads. We achieve this through a distribution-aware trajectory sampling mechanism, which selects trajectories from a redundant exploration space for each prompt, and an adaptive redundancy allocation scheme to maximize both shaping effectiveness and system efficiency. Experiments demonstrate significant acceleration over state-of-the-art systems by up to 1.77x without compromising model performance.

On-policy distillation transfers reasoning capabilities by training a student model on its own generated trajectories using token-level feedback from a teacher. However, we identify a critical bottleneck, \textbf{Supervision Fidelity Decay (SFD)}: as student-generated prefixes lengthen, the teacher's next-token distribution becomes less confident and less discriminative. Consequently, the teacher-dependent corrective signal in reverse-KL distillation weakens, causing student drift to compound across long reasoning chains. To mitigate SFD, we introduce \textbf{Lookahead Group Reward (\ours{})}. Building on the insight that next-step teacher confidence reflects the discriminative strength of future reverse-KL supervision, \ours{} evaluates the student's top-K candidate tokens by the teacher confidence they induce at the subsequent step and assigns a group-normalized reward. To maintain computational efficiency, we further design an entropy-triggered tree-attention mechanism. Across six math and code benchmarks, \ours{} improves mean@8 by \textbf{2.57} points over OPD for a 7B student, with gains increasing in longer-generation and reaching +\textbf{4.92} points on AIME-26 at 39k tokens.

Reinforcement Learning from Verifiable Rewards (RLVR) has improved language models in domains such as mathematics and code, where correctness can be checked automatically. However, many important tasks are only partially verifiable: prompts contain multiple requirements, responses may satisfy some but not all of them, or no single reference answer might exist. We introduce Soft-RLVR, a framework for reinforcement learning from decomposed, learned verification signals. Soft-RLVR converts each prompt into a checklist of atomic requirements, scores candidate responses item by item with an LLM verifier, and trains on the resulting soft reward. Checklist-based rewards turn sparse pass/fail supervision into a denser partial-credit signal, but they also introduce a tradeoff: averaging item-level judgments can reduce verifier noise, while partial credit can reward incomplete responses. We formalize this tradeoff and identify conditions under which checklist-based verification gives a more reliable RL training signal than holistic verification. We further introduce Soft-SVeRL, a self-verifying variant of Soft-RLVR in which the policy also acts as the verifier. We show that self-verification is prone to reward inflation from overly permissive self-judgments, and that explicit stabilization is needed to prevent this collapse. In a controlled instruction-following setting with rule-based ground-truth evaluation, checklist-based Soft-RLVR improves IFEval by up to 11.1 points using only learned verifier rewards. Our experiments further show that verifier quality and checklist quality both affect downstream RL outcomes, and that explicit stabilization is essential for effective self-verification.

Reinforcement learning has become a central paradigm for advancing reasoning in large language models, yet most existing methods still depend on stronger teacher models or heavily curated difficult datasets, limiting scalable capability improvement. In this paper, we introduce DenoiseRL, a reinforcement learning framework that substitutes external supervision with recovery-oriented optimization over failures from weak models. Instead of relying on stronger supervision or carefully engineered data, DenoiseRL learns directly from incorrect reasoning traces by converting them into opportunities for improvement, making training more scalable and less dependent on external resources. This yields a richer and more diverse learning signal, improving exploration efficiency from imperfect model behavior. As a result, DenoiseRL improves reasoning performance and overall training efficiency while reducing the need for expensive data curation or stronger teacher models. Empirically, DenoiseRL consistently outperforms strong on-policy RL baselines across competitive mathematical and general reasoning benchmarks and promotes stronger self-corrective behavior as training difficulty increases, highlighting an effective and scalable alternative pathway for improving reasoning in large language models.

Reinforcement learning with verifiable rewards improves language model reasoning, but its reliance on domain-specific verifiers, sparse outcome rewards, and coarse-grained credit assignment limits its applicability. We introduce GeneralThinker, an on-policy framework that reformulates reasoning supervision as dense answer-conditioned optimization, enabling response-level evaluation and token-level credit assignment without domain-specific verifiers. GeneralThinker evaluates generated reasoning trajectories using the likelihood of the ground-truth answer and derives token-wise compatibility signals for fine-grained credit assignment. To stabilize optimization, it constrains token-level updates through clipping and direction-preserving modulation. Across 11 benchmarks spanning mathematics, STEM, and general reasoning, GeneralThinker achieves the best average performance. Further analyses show that uncontrolled token-level modulation can destabilize training, whereas controlled modulation makes fine-grained credit assignment consistently effective.

Off-policy reinforcement learning of pretrained flow policies remains challenging due to the instability of optimization arising from the multi-step sampling process. Recently, Q-learning with Adjoint Matching (QAM) addressed this by recasting policy improvement as a stochastic optimal control (SOC) problem guided by a learned critic. However, QAM inherits a fundamental fragility of critic-guided improvement, since small critic errors can be exponentially amplified and often lead to performance collapse. This paper introduces Trust Region Q Adjoint Matching (TRQAM), a stable off-policy fine-tuning algorithm that adaptively controls the path-space KL between the fine-tuned and pretrained policies through projected dual descent. Specifically, we adapt a trust-region parameter $λ$ inside the sampling process of the flow policy and prove that $λ$ exactly weights the path-space KL in the SOC objective. As a result, our method can tightly control the deviation from the pretrained policy within a prescribed KL budget, achieving stable off-policy RL. Through experiments on 50 OGBench tasks, TRQAM consistently outperforms prior methods in both offline RL and offline-to-online RL. In particular, TRQAM achieves an overall success rate of 68% in offline RL, substantially improving over the strongest baseline at 46%.

Reinforcement learning in open-ended long-form generation is challenging because reliable reference answers and automatic metrics are often unavailable. Existing rubric-based methods typically rely on pointwise LLM-as-a-judge scoring, but absolute scores are difficult to calibrate across complex responses, may provide weak discrimination among same-query rollouts, and can become saturated during optimization. We propose Tournament-GRPO, a group-wise reward framework that converts rubric-guided LLM judgments into relative rewards through repeated multi-round tournaments among same-query rollouts. Tournament-GRPO compares candidates within groups, accumulates tournament outcomes, and normalizes them into group-wise rewards for GRPO training. Experiments on Deep Research Bench show that Tournament-GRPO consistently outperforms existing reward-design baselines, achieving a 4.52-point overall-score improvement over the strongest baseline. Further analyses show that tournament rewards provide a favorable effectiveness--efficiency trade-off and that tournament design affects training dynamics. These results suggest that rubric-guided tournament comparison provides an effective reward signal for reinforcement learning in open-ended long-form generation.

The open-ended generation in LLMs usually requires multi-dimensional rubrics to adequately assess quality and guide the improvement of reinforcement learning. However, a critical dilemma inherent in this training paradigm is the imbalanced reward polarization along different rubric dimensions. Under this bottleneck, even if LLMs achieve relatively high rewards after training, they may still exhibit severe deficiencies in certain dimensions, leading to a direct deterioration in user experience. To address this problem, we propose Focal Reward, a novel objective to automatically balance the training of reinforcement learning under rubric-based rewards. Specifically, we first leverage an inverse reward projection mechanism to estimate the saturation degree of each criterion in the rubric, which forms the basis to calibrate the reward direction. Then, the final objective is designed with an automatically reweighting coefficient for each criterion to achieve the fine-grained balancing. Extensive experiments across three model scales and six benchmarks demonstrate that our Focal Reward method outperforms the strongest static aggregation baseline in all 18 model-benchmark comparisons. Rollout, mechanism, and ablation analyses further show that these gains arise from online, saturation-aware reallocation toward rubrics that still have room for improvement.

Multi-trait essay scoring aims to provide fine-grained evaluation of writing quality across multiple dimensions. However, how to effectively post-train autoregressive scoring models remains underexplored. In this paper, we propose Trait-Aware Policy Optimization (TAPO), a post-training framework tailored to autoregressive multi-trait scoring. Our method decomposes rewards along both the sample and trait dimensions, combining global scoring consistency, trait-level accuracy, format validity, and inter-trait dependency preservation. In addition, we use enhanced prompts throughout training by incorporating original prompt texts and trait descriptions, providing richer semantic information for trait-specific score generation. Experiments across multiple backbone models show that our method consistently improves multi-trait scoring performance over supervised fine-tuning and scalar-reward optimization baselines, demonstrating the effectiveness and transferability of trait-aware post-training for essay scoring.