Reinforcement_Learning
-
LoCA: Local Credit Assignment for Reinforcement Learning of Autoregressive Flow-Matching TTS
2026-10-20 11:23:47Jie Liu, Junyu Zhou, Junhao Zhong, WeiSen Tang, Rukai Cai, Haoyue Zhan, Ruiqi Xing, Ling LongAbstract
Reinforcement learning can improve text-to-speech synthesis through feedback on generated speech. However, sentence-level rewards do not identify local errors, while signed regression updates can lead to excessive fitting or repulsion of sampled outputs. We propose LoCA (Local Credit Assignment) for autoregressive flow-matching text-to-speech. LoCA uses ASR-based text alignment to locate content errors in generated speech and redistribute sentence-level advantages across acoustic frames. To improve training stability, we introduce reference-relative positive and negative thresholds that limit continued fitting and repulsion. Experiments on VoxCPM2 show that LoCA reduces sample-weighted content error on a multilingual CV3 evaluation subset by 20.5% and 14.3% relative to the pretrained backbone and GROW, respectively, while improving speaker similarity. LoCA also improves content accuracy on the Seed-TTS-Eval hard subset. Ablation results support the contributions of local credit and threshold-based regression control.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28035
PDF
-
From RL Papers to Framework Code: Inclusion and Review in Seven Open-Source Training Frameworks
Abstract
Practitioners use reinforcement learning methods for language models through training frameworks, so a method that a framework includes is one configuration change away for its users. We measure how often this happens. We trace seven open-source frameworks for RL post-training through their commit histories and link them to 6,939 screened arXiv papers from January 2025 to June 2026. Of 1,598 papers that propose a general RL training method, 37 reached at least one framework. Across five quarterly cohorts of papers, the number included within 180 days stayed between 5 and 7 while the cohorts grew from 72 to 386 papers. Compared with papers from the same quarters, included papers more often trained policies of 30B parameters or more, at 41 against 10 percent, and more often changed a coefficient, clip, mask or weight in the existing loss, at 29 against 9 percent. Both gaps hold without papers from the companies that maintain the frameworks, while code release was equally common in both groups. The frameworks' issues and pull requests show that few methods are turned away in public. More than nine in ten of the general methods no framework included have no thread there that cites or names them, and many proposals that do appear stay open without a reply. Two further records, the frameworks' issues and the technical reports of 13 large open-weight models, show that users rarely report training failures in public and that the reports state 8 of the 13 widely included methods. We release the data as a tracker that links training failures to framework implementations and lists each framework's contribution rules and earlier proposals.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28027
PDF
-
Reinforcement learning for hardware acceleration and system-level optimization on FPGA and integrated-circuit platforms: A survey
2026-10-20 11:15:34Hamza KheddarAbstract
Reinforcement learning (RL) enables adaptive and autonomous decision-making in embedded, edge, and heterogeneous computing systems. Field-programmable gate arrays (FPGAs) and integrated circuits (ICs) offer low latency, energy efficiency, and architectural flexibility for RL deployment, while introducing challenges in resource constraints, implementation complexity, and hardware-algorithm co-design. This review surveys more than 100 studies on RL implementations across FPGA and IC platforms, emphasizing architectures, implementation strategies, performance evaluation, and applications. The literature is organized by RL family, including model-based Markov decision processes, classical value-based methods, deep RL, actor-critic, policy-gradient, and multi-agent approaches. We further classify studies by abstraction level, hardware realization strategy, and application domain, examining how RL algorithms map onto reconfigurable and fixed hardware. Unlike surveys restricted to particular algorithms or platforms, this work provides a unified analysis of FPGA and IC implementations, covering acceleration, reconfigurable architectures, energy-aware control, and system-level optimization. Comparative assessments consider resource utilization, latency, throughput, power consumption, and reported performance gains. Finally, we identify recurring architectural patterns, practical limitations, open challenges, and research directions for efficient RL-driven hardware systems. The survey offers a consolidated reference for researchers developing and evaluating RL solutions on specialized hardware.
Abstract (translated)
URL
https://arxiv.org/abs/2610.28699
PDF
-
From Comparison to Selection: Enhancing Cross-Scale Generalization of Pointer Networks Trained with Reinforcement Learning for Capacitated Drone Delivery Routing
2026-10-20 09:44:49Sofiene Lassoued, Devara Tertia, Stefan Lier, Andreas SchwungAbstract
Unmanned aerial vehicles (UAVs) enable fast, flexible last-mile and emergency delivery, but their routing remains challenging as the number of clients varies. Classical approaches based on mixed-integer programming and heuristics can scale poorly or require problem-specific design, motivating learning-based alternatives. Reinforcement learning is particularly promising, provided a single policy can generalize across problem sizes without retraining. Although attention-based Pointer Networks are inherently size-agnostic, their solution quality degrades under both upscaling and downscaling. Using the Capacitated Vehicle Routing Problem (CVRP) as a controlled proxy, with fixed capacity reflecting drone payload constraints, we investigate this degradation and identify three contributing factors: shifts in node density, attention dispersion, and dilution of the mean-pooled graph context. We systematically compare architecture-wide, encoder-side, and decoder-side modifications to address these limitations and propose a learned, permutation-invariant graph-context aggregation mechanism, implemented as a weighted average and as Set2Set. Results reveal distinct requirements for transfer in each direction: entropy-based attention scaling reduces the CVRP20-to-CVRP100 performance gap by 1.41 percentage points, while the proposed aggregation methods achieve the largest improvement on the more challenging CVRP100-to-CVRP20 transfer, approximately 0.9 percentage points. Exploiting this complementarity, we introduce an approach selector that chooses the best model for each training-target size pair. The selector reduces cost relative to the reference model across all nine seen train-test pairs and eight of nine pairs involving unseen sizes (CVRP35, CVRP75, and CVRP200), achieving improvements of up to 3.2 percent.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27936
PDF
-
SAPD: Learning from Agent Experience without Environment Interaction
2026-10-20 08:30:30Juncheng Diao, Haibin Wang, Wei Shi, Yifan Ding, Qingbin Li, Rongxiang Weng, Xunliang CaiAbstract
Scaling the training of Large Language Model (LLM) agents typically requires a large collection of executable environments, whose construction, maintenance, and operation constrain the expansion of training experience. Existing offline trajectories offer an opportunity to reuse interaction experience, yet effectively refining the current policy without revisiting these environments remains challenging: supervised fine-tuning (SFT) can lead to catastrophic forgetting, while online reinforcement learning requires real-time interaction with the environment. To address this challenge, we propose Step-Advantage Policy Distillation (SAPD), a method for learning from offline trajectories using relative step advantages. SAPD decomposes multi-turn trajectories into individual decision contexts for on-policy distillation, allowing the student to generate responses conditioned on recorded histories, and introduces relative step advantage signals to stabilize training. The entire process requires neither new environment observations nor additional multi-turn interactions. Experiments on ALFWorld, WebShop, and Search-based QA show that SAPD improves performance across different teacher configurations, mitigates catastrophic forgetting compared with SFT, and runs at least $4.7\times$ faster per training step than online OPD. We will release our code soon.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27847
PDF
-
RoboJudge: Multimodal Language Models as Judges for Embodied Video Generation
2026-10-20 07:48:41Siyuan Ma, Yu Qi, Cheng Ye, Ruotian Peng, Xinyi Xu, Zitiantao Lin, Zedong Cai, Yijian Huang, Weiyang Liu, Siyuan Wang, Yandong WenAbstract
Video generation models are promising foundations for embodied world models, but only if their generated rollouts are physically valid and faithful to task instructions. Multimodal large language models (MLLMs) are increasingly used to judge these properties, yet their agreement with human judgments on embodied videos has not been systematically evaluated. To address this gap, we introduce RoboJudge-Bench, a benchmark for evaluating MLLMs as judges of embodied video generation. The benchmark measures two fundamental dimensions, Physical Adherence and Instruction Alignment, across 800 human-annotated videos from 8 source corpora and 10 video generators, spanning grippers, human hands, and dexterous hands. Experiments reveal uneven alignment between existing judges and human ratings: general-purpose MLLMs show lower agreement on physical adherence, while specialized video judges designed for general-domain physical reasoning do not consistently transfer to embodied scenarios. Motivated by these findings, we construct RoboJudge-Train, comprising 12K videos annotated with 25K human-verified scores and model-assisted rationales for Physical Adherence and Instruction Alignment. We fine-tune a 9B MLLM on this dataset with supervised learning followed by reinforcement learning, yielding RoboJudge-9B. Among the model judges evaluated on RoboJudge-Bench, RoboJudge-9B achieves the highest overall agreement, reaching a Pearson correlation of 0.719 with a statistically significant 0.089 gain over Gemini-3.7-Flash, the best-performing proprietary baseline in our evaluation. Training on RoboJudge-Train also yields gains on external benchmarks, including VideoPhy2 and Physion-Eval. We further use RoboJudge-9B as a downstream evaluator to benchmark video generation models according to Physical Adherence and Instruction Alignment.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27782
PDF
-
Learning Native Reflection in Unified Models with Interleaved Reinforcement Learning
2026-10-20 07:26:16Yijia Fan, Ziqi Huang, Zhongang Cai, Yan Li, Zimo Wen, Wanqi Yin, Haiwen Diao, Ziwei LiuAbstract
Unified multimodal models can both look at and render images, so in principle they can repair their own generations: diagnose what an image gets wrong, revise it, observe the result, and diagnose again. Whether a revision helps is known only after it is rendered, so the reflection text and the image generation must be learned jointly, over the whole loop. Supervised fine-tuning (SFT) on reflection trajectories gives a cold start but does not find the high-success repair paths, and naive RL that optimizes only the renderer or only one head leaves most of the gain untapped. We introduce UMM-Reflection, which applies reinforcement learning (RL) to complete reflection trajectories inside one unified model: sibling trajectories share one initial image, so the group-relative advantage compares reflection strategies, and one trajectory-level advantage updates both the reflection tokens and the flow-based revisions, avoiding the combinatorial blow-up of per-round credit assignment. Unlike single-round editing or pipelines with an external critic, credit flows across rounds and to both roles of the same model, and no verifier is needed at inference. On BAGEL, UMM-Reflection improves GenEval by 12.05 points over SFT, and the gains transfer to WISE (+10.97), OneIG-Bench (+3.48), and T2I-CompBench++ (+4.63), none of which is used in training.
Abstract (translated)
URL
https://arxiv.org/abs/2609.35767
PDF
-
RSI Control: Can AI Models Perform Covert Sabotage in the Self-Improvement Process?
2026-10-20 06:57:59Kaiwen Zhou, Udari Madhushani SehwagAbstract
Recursive self-improvement, in which frontier AI models work on training the next generation, is quickly becoming a reality. However, the safety of this process has received far less attention than it should. A misaligned model training its successor can shape what that successor knows, how it behaves, and what it wants, and the harm carries forward into the next generation. We study this risk through the lens of AI control. We introduce RSI Control Arena, a testbed in which a frontier model, acting as an autonomous R\&D agent, is given a benign main task from a stage of a successor model's training pipeline together with a covert side task to install a misaligned property in the successor. The testbed contains 16 side tasks in three classes, forming 22 task pairs with main tasks that span the pipeline from data curation to reinforcement learning. We evaluate six frontier models as agents against LLM monitors that read the transcript of the run and the agent's reasoning. We observe that every model completes a substantial share of the side tasks without degrading the main-task performance, including side tasks that make the successor itself a better saboteur. Under minimal instructions to stay covert, models already produce successful attacks that monitors fail to detect, and providing a short list of evasion tactics further reduces the detection rate. Monitors with access to agent's reasoning detects most attacks, but not all. Our results indicate that recursive self-improvement raises significant safety concerns, and that strong safety effort should be in place before models are trusted with greater responsibility of training their successors.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27735
PDF
-
Prescribed Performance Guided Safe Reinforcement Learning for Roundabout Navigation of Autonomous Vehicles
2026-10-20 06:54:57Wenhan Li, Yangrui Zhang, Hang Zhou, Peiran Liu, Yiding JiAbstract
Connected and Autonomous Vehicles (CAVs) face significant challenges in roundabout navigation due to dense traffic interactions and unpredictable agent behaviors, necessitating high levels of adaptability and safety. While the combination of Reinforcement Learning (RL) and Model Predictive Control (MPC) offers a promising approach, existing frameworks suffer from a structural mismatch where pointwise RL decisions fail to align with MPC's trajectory level optimization, and often lack rigorous safety guarantees. This work proposes RLTrajGen-PPMPC-CBF, a hierarchical framework for safe, smooth and comfort roundabout navigation, which regulates the coupling between RL-based planning and MPC-based control. We employ Prescribed Performance Constraints (PPC) to enforce a gradual, stable convergence between reference trajectories and control outputs, ensuring MPC tracking performance remains consistent with intended behavior from RL. Additionally, a Control Barrier Function (CBF) layer provides real-time safety corrections that are fed back into the RL process. Simulation results in the MetaDrive environment demonstrate that our method achieves a 6.25\% increase in average success rate and a 65.87\% reduction in Motion Sickness Dose Value (MSDV) compared to the optimal baseline, meanwhile accelerating training convergence.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27732
PDF
-
Reusing Multimodal Agents: Efficient Evaluation of Sound Designs in Games
2026-10-20 05:36:58Thai Nguyen Van, Ibrahim Khan, Mury Fajar Dewantoro, Pratch Suntichaikul, Hai Van Pham, Ruck ThawonmasAbstract
This paper introduces a novel framework for efficiently evaluating in-game sound designs using multimodal learning and reinforcement learning. Sound design significantly influences gameplay and accessibility; however, objective evaluation methods, defined here as automated assessments based on agent performance rather than human ratings, often require retraining agents from scratch for each sound design. Our approach first pre-trains a multimodal encoder that encodes visual and auditory information into a shared latent space. A reinforcement learning agent is then trained using this latent representation. We fine-tune the multimodal encoder for each sound design while keeping the trained policy fixed, allowing us to isolate the effects of sound changes on agent behavior. To evaluate the proposed method, we conducted experiments on games from multiple genres, comparing the performance of blind agents (agents using only sound input) under various sound designs. Experimental results suggest that this approach can detect differences in agent performance caused by degraded or altered sound design. Moreover, we significantly reduce the computational cost compared to retraining the agent from scratch. Experimental results suggest that this approach provides a practical and scalable solution for evaluating in-game sound designs. The source code, data and supplementary document are available: this https URL.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27670
PDF
-
Policy Search in Code Space for Multi-Agent Pathfinding
2026-10-20 03:42:05Matthias Eder, Pantelis Emmanouil, Vivek Farias, Fabian Fischer, Adam Jozefiak, Tianyi Peng, Thomas Ulz, Raphael Watschinger, Fangyu Wu, Andrew ZhengAbstract
Developing coordination policies for complex multi-agent systems relies on either labor-intensive algorithm design or opaque task-specific reinforcement learning. With recent advances in autonomous coding agents, we show that policy search directly in code space offers a compelling third path that combines automated optimization with explicit interpretability. We investigate a human-directed workflow in which coding agents iteratively propose, implement, evaluate, diagnose, and eventually refine algorithms guided by simulation feedback and explicit correctness verification. We conducted two case studies and found that this workflow robustly outperformed any manually engineered solutions. On a challenging map in the 2024 League of Robot Runners competition, a two-day search discovered a policy that exceeds the stronger locally reproduced competition entry by 35.0% on the densest instance and generalizes to unseen map instances. In simulated real-world warehouses with irregular lanes, continuous robot geometry, and asynchronous motion, a week-long search discovered an entirely new class of multi-agent pathfinding algorithm that outperforms a calibrated proprietary solution in throughput by 58.9%. Under stated assumptions, we further prove that the new algorithm is collision-free and completes, in finite time, every accepted goal that is not withdrawn or replaced. Together, the studies show that policy search in code space powered by state-of-the-art coding agents offers a highly competitive path to building real engineering solutions that are both effective and analytically tractable.
Abstract (translated)
URL
https://arxiv.org/abs/2610.25946
PDF
-
Expected Return Causes Outcome-Level Mode Collapse in Reinforcement Learning and How to Fix It with Inverse Probability Scaling
2026-10-20 03:12:50Abhijeet Sinha, Sundari Elango, Dianbo LiuAbstract
Many reinforcement learning (RL) problems admit multiple terminal solutions of comparable quality, where the goal is not to identify a single optimum but to represent a diverse set of high-quality outcomes. Nevertheless, policies trained by standard expected return maximization routinely collapse onto a small subset of outcomes, a phenomenon commonly attributed to insufficient exploration or weak regularization. We show that this explanation is incomplete: outcome level mode collapse is a structural consequence of the expected-return objective itself. Under idealized learning dynamics, the log-probability ratio between any two outcomes evolves linearly in their reward difference, implying exponential ratio divergence and inevitable collapse independent of the exploration strategy, entropy regularization, or optimization algorithm. We identify the source of this pathology as the probability multiplier inside the expectation and propose a minimal correction: inverse probability scaling, which removes outcome-frequency amplification from the learning signal, fundamentally changes the learning dynamics, and provably yields reward-proportional terminal distributions, preventing collapse in multimodal settings. We instantiate this principle in Group Relative Policy Optimization (GRPO) as a drop-in modification, IPS-GRPO, requiring no auxiliary models or architectural changes. Across different reasoning and molecular generation tasks, IPS-GRPO consistently reduces outcome-level mode collapse while matching or exceeding baseline performance, suggesting that correcting the objective rather than adding exploration heuristics is key to reliable multimodal policy optimization.
Abstract (translated)
URL
https://arxiv.org/abs/2601.21669
PDF
-
HealBench: A Fine-Grained Benchmark for Evaluating Psychological Comfort in Text-to-Image Generation
2026-10-20 02:31:31Junjie Xu, Yuzhe Yang, Rui Yang, Luwei Xiao, Wenxin Wu, Xingjiao Wu, Liang HeAbstract
Despite advances in photorealism, semantic fidelity, and aesthetics, text-to-image generation and image editing remain understudied in a human-centered dimension: whether their outputs feel psychologically comforting. Grounded in cognitive evaluation theory, we define psychological comfort as an affective response shaped by viewers' appraisal of restorative and emotionally supportive visual cues. We introduce HealBench, a fine-grained benchmark of 30,000 high-quality image-text pairs spanning 19 categories and 92 subcategories, selected from 100,000 candidates through a human- and expert-in-the-loop pipeline combining vision-language model matching, human preference models, expert filtering, and exemplar-guided augmentation. We also construct HealBench-Eval, a feature-clustered evaluation set of 1,095 instances. Using HealBench-Eval, we conduct objective and subjective evaluations of 14 representative image generation models and prompt-rewriting strategies. Results reveal a gap between conventional visual quality and perceived comfort: strong semantic alignment and aesthetics do not guarantee emotionally restorative images. Reinforcement learning experiments further show that HealScorer can serve as a reward signal for assessing and improving the emotional and restorative quality of generated images. These findings establish psychological comfort as a distinct dimension of human-centered image generation and position HealBench as a foundation for affect-aware generative models.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27516
PDF
-
How Data Scales in Agentic Reinforcement Learning: Laws and Synthesis Strategies
2026-10-20 01:59:17Bowei He, Yankai Chen, Xiaokun Zhang, Changjiang Han, Ye Yuan, Chong Li, Xue LiuAbstract
Pretraining scaling laws treat training data as a one-dimensional quantity: a token count. Agentic reinforcement learning (RL) inherits this scalar abstraction, but modern synthesis pipelines now generate \textit{tasks}, \textit{environments}, and \textit{trajectories} independently and at very different costs, turning data into a structured design space. This raises a question pretraining never had to answer: given a synthesis budget, \textit{which axis} should be scaled? We address this question end-to-end with three tightly coupled contributions. First, we decompose agentic data into three cardinality axes (task, environment, trajectory), plus a reward-density control variable, and fit per-axis scaling relations on different large language models (LLMs) across math+code, SWE, web, and UI/tool application domains. Across all model sizes, model families, domains, and RL algorithms (PPO and GRPO) we measured, the scaling exponents order as environment $>$ task $>$ trajectory. When environment diversity is decomposed into world and environment-structure diversity, its advantage is mainly driven by the former, while the latter is just comparable to the task diversity. Second, we use the fitted laws as a common ruler to price synthesis methods, capturing each method's efficiency as a per-axis discount factor and identifying critical synthetic-to-real ratios at which collapse begins; these ratios differ by an order of magnitude across axes. Third, we cast budget allocation as a constrained optimization under our laws and discounts, deriving a Chinchilla-style compute-optimal recipe and validating it at held-out scale. The empirical results demonstrate that following the recipe yields up to $1.7\times$ compute efficiency over the dominant ``scale-the-trajectories'' practice.
Abstract (translated)
URL
https://arxiv.org/abs/2610.23946
PDF
-
Diffusion Subgoal Planning for Long-Horizon Offline Goal-Conditioned Reinforcement Learning
2026-10-20 00:56:00Hengrui Zhang, Yuhu Cheng, C. L. Philip Chen, Xuesong WangAbstract
Offline goal-conditioned reinforcement learning (GCRL) learns goal-directed policies from reward-free data, but in long-horizon tasks, goal-conditioned value functions often provide unstable guidance due to sparse rewards and discounting. Hierarchical methods partially mitigate this issue via subgoal decomposition; however, high-level decision-making still relies on noise-sensitive value estimates, leading to unstable behavior in complex environments. We address this limitation by proposing \textbf{D}iffusion \textbf{S}ubgoal \textbf{P}lanning (\textbf{DSP}), a diffusion-based framework for high-level subgoal generation. DSP casts high-level planning as guided generative inference over goal-conditioned subgoals and learns both conditional and unconditional flows, enabling classifier-free guidance to introduce a goal-directed bias at inference time. By removing explicit value-based guidance from high-level planning, DSP generates reachable and goal-directed subgoals through a generative model while retaining hierarchical execution. Experiments on offline GCRL benchmarks demonstrate that DSP outperforms prior methods on a range of navigation and manipulation tasks, with particularly strong performance in maze environments that require multi-step subgoal planning.
Abstract (translated)
URL
https://arxiv.org/abs/2609.34575
PDF
-
Look Before You Reason: Implicit Visual Thinking for Efficient Multimodal Reasoning
2026-10-19 22:11:24Zerui Chen, Changrui Chen, Fei Ni, Jiankang DengAbstract
Vision-language models (VLMs) have advanced rapidly in multimodal reasoning, yet they remain limited on tasks requiring fine-grained understanding of small or easily overlooked image regions. Recent thinking with images approaches mitigate this limitation by allowing models to inspect images through operations such as zooming, cropping, or code execution. While effective, their multi-turn interactions with VLMs introduce redundant token computation and slow inference, and separate region inspection from the reasoning step that depends on it. To address these issues, we propose Look Before You Reason (LoRe), an implicit visual thinking framework for efficient visual reasoning within a single-turn VLM interaction. Given an image and a question, LoRe predicts the most relevant image region, aligns it with the corresponding image patch features, and strengthens the associated key-value (KV) cache entries, enabling subsequent decoding to directly exploit the selected visual cues without additional visual inputs or explicit tool calls. We further employ reinforcement learning to guide the VLM toward identifying informative image regions and leveraging them during reasoning. To support fine-grained evaluation of multimodal reasoning, we introduce COCO-ObjQA, a large-scale benchmark for object-centric multimodal reasoning. Experiments on three challenging multimodal benchmarks demonstrate that LoRe consistently improves VLM reasoning performance with low additional inference overhead.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27341
PDF
-
Vulnerability Analysis for Safe Multi-Agent Reinforcement
2026-10-19 21:09:02Taozheng Zhu, Shixiong Jiang, Fanxin KongAbstract
Safe Multi-Agent Reinforcement Learning (SMARL) aims to learn cooperative control policies under prescribed safety constraints. Al- though existing SMARL methods focus on enforcing safety during policy optimization, their vulnerability remains largely unexplored. This paper investigates inference-time observation attacks against SMARL, where an adversary perturbs the observations of a subset of agents, thereby altering the actions produced by their policies. We propose MinMax Attack, an attack framework that jointly selects adversarial target actions for compromised agents while accounting for the Cooperative Resistance of benign agents. We further derive a bound on the induced safety cost and characterize its relation- ship with the Compromised-Agent Budget and the Perturbation Budget. Experiments across multiple safety-critical multi-agent benchmarks and representative state-of-the-art SMARL algorithms show that MinMax Attack induces substantially higher safety costs than existing attack baselines while preserving task reward, thereby reducing its detectability and achieving both attack effectiveness and stealthiness.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27293
PDF
-
VPFlow: Value-Predictive Planning with Imperfect World Models for Offline Goal Reaching
2026-10-19 20:55:03Yunzhe Hu, Dong XuAbstract
Offline goal-conditioned reinforcement learning enables skill acquisition by reaching any goal from any state without dense rewards. Model-based methods allow for planning by scaling test-time compute to solve complex tasks. Combining both holds appealing promise for pre-training on suboptimal demonstrations and zero-shot adaptation via goal specification and planning. Yet existing methods assume effective planning requires accurate next-state prediction in pixel or latent space. In this work, we show that value prediction is more useful for planning, whereas accurate state prediction is often unnecessary. Our key insight is that offline goal reaching naturally admits a closed-form Monte Carlo return, enabling value regression to replace temporal-difference bootstrapping. We use this return as the sole supervision for latent world models: imagined latents are trained to predict goal-reaching value rather than match future states, implicitly preventing representation collapse. These planning-oriented representations let imperfect world models imagine on the level sets of value field beyond dataset transitions. We then present VPFlow, a value-predictive planner that pairs the world models with a one-step flow policy and plans in its noise space via evolutionary search. It enables policy improvement with imagined generalized advantage and reduces out-of-distribution queries common in action-space planning. On 30 state and pixel OGBench datasets, VPFlow surpasses model-free baselines by at least 30.3 and 10.1 percentage points in success rate, respectively, and outperforms latent planners LeWorldModel, PLDM, and TD-MPC2. It achieves this despite a latent prediction error orders of magnitude larger than with state prediction, while minimizing this error lowers success rate. This demonstrates that value-predictive representations, not exact state prediction, are what offline planning requires.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27280
PDF
-
A latent control model for realistic rodent motion
2026-10-19 20:54:21Aidan Sirbu, Charles Y. Zhang, Yuanjia Yang, Bence P. \"Olveczky, Talmo D. Pereira, Blake A. RichardsAbstract
The development of embodied models of animal behavior is a major goal of the neuro-AI community. Embodied models will enhance our ability to make direct comparisons between biological and artificial agents. To make such comparisons effective, though, we need embodied models that actually move like animals. Previous work has developed virtual animal bodies and techniques for training realistic motion through imitation. However, to date, there is no system for embodied animal modeling that produces natural movements both during trained goal-directed behavior, and during exploration driven by random generation. Here, we introduce Simulated Control via Augmented Motor Priors for Embodied Reinforcement learning (SCAMPER), a system for training an embodied virtual rat model, enabling natural movements during both goal-directed behavior and random exploration. SCAMPER uses a variational architecture with two distinct priors, a motion prior for control and a behavior prior for exploration. We show that combining both of these priors allows SCAMPER to generate realistic behavior during exploration and exploit the task structure effectively. SCAMPER can also learn from sparse rewards as a result of the diverse movements induced by the behavior prior, allowing the system to model realistic sparse-reward tasks from experimental neuroscience. Altogether, SCAMPER provides the neuro-AI community with an effective new system for training embodied models of rodents on realistic tasks.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27279
PDF
-
CEFR-oriented Russian Text Simplification Using Reinforcement Learning
2026-10-19 20:04:47Kristina Mustakova, Alexey SorokinAbstract
We present a study on controlled automatic simplification of Russian texts using preference-based optimization algorithms with a focus on adapting texts to the A1, A2 and B1 proficiency levels. We fine-tune YandexGPT using Rejection Sampling and Direct Preference Optimization (DPO) methods to improve control over the complexity of the generated text. We compare several training configurations that differ in dataset composition, text type and the strategy used to construct preference pairs for DPO. For automatic evaluation we train a regression model based on ruRoBERTa-large to predict continuous complexity scores corresponding to CEFR levels. We also consider semantic similarity, lexical coverage and quantitative readability metrics. Human evaluation assesses simplicity, fluency and adequacy. Our best model achieves 87.15\% target level accuracy, an MAE of 0.35 CEFR levels and a target interval MAE of 0.11. Manual assessment shows that 75% of the evaluated simplifications match the target morphological and syntactic level, and fluency and adequacy scores are especially high for A2 and B1. Although A1 remains the most challenging level, the model significantly reduces the proportion of vocabulary and grammatical constructions beyond the target level while generally preserving meaning. Our model is freely available on $\href{this https URL}{HuggingFace}$.
Abstract (translated)
URL
https://arxiv.org/abs/2610.27237
PDF
