Animals achieve energy-efficient locomotion by their implicit passive dynamics, a marvel that has captivated roboticists for decades.Recently, methods incorporated Adversarial Motion Prior (AMP) and Reinforcement learning (RL) shows promising progress to replicate Animals' naturalistic motion. However, such imitation learning approaches predominantly capture explicit kinematic patterns, so-called gaits, while overlooking the implicit passive dynamics. This work bridges this gap by incorporating a reward term guided by Impact Mitigation Factor (IMF), a physics-informed metric that quantifies a robot's ability to passively mitigate impacts. By integrating IMF with AMP, our approach enables RL policies to learn both explicit motion trajectories from animal reference motion and the implicit passive dynamic. We demonstrate energy efficiency improvements of up to 32%, as measured by the Cost of Transport (CoT), across both AMP and handcrafted reward structure.

Multimodal text-to-image generation remains constrained by the difficulty of maintaining semantic alignment and professional-level detail across diverse visual domains. We propose a multi-agent reinforcement learning framework that coordinates domain-specialized agents (e.g., focused on architecture, portraiture, and landscape imagery) within two coupled subsystems: a text enhancement module and an image generation module, each augmented with multimodal integration components. Agents are trained using Proximal Policy Optimization (PPO) under a composite reward function that balances semantic similarity, linguistic visual quality, and content diversity. Cross-modal alignment is enforced through contrastive learning, bidirectional attention, and iterative feedback between text and image. Across six experimental settings, our system significantly enriches generated content (word count increased by 1614%) while reducing ROUGE-1 scores by 69.7%. Among fusion methods, Transformer-based strategies achieve the highest composite score (0.521), despite occasional stability issues. Multimodal ensembles yield moderate consistency (ranging from 0.444 to 0.481), reflecting the persistent challenges of cross-modal semantic grounding. These findings underscore the promise of collaborative, specialization-driven architectures for advancing reliable multimodal generative systems.

Hallucination and factuality deficits remain key obstacles to the reliability of large language models (LLMs) in long-form generation. Existing reinforcement learning from human feedback (RLHF) frameworks primarily rely on preference rewards, yet they often overlook the model's internal knowledge boundaries, exacerbating the so-called "hallucination tax". To address this challenge, we propose Knowledge-Level Consistency Reinforcement Learning Framework (KLCF), a novel framework that focuses on the knowledge consistency between the policy model's expressed knowledge and the base model's parametric knowledge, and introduces a Dual-Fact Alignment mechanism to jointly optimize factual recall and precision. Specifically, KLCF leverages pretrained knowledge boundaries to construct fact checklist, guiding online reinforcement learning to improve factual coverage and recall; simultaneously, it trains a self-assessment module based on the base model's internal knowledge to enhance factual precision during generation. Unlike prior methods that rely on external retrieval or heavy verification, our reward design is fully external-knowledge-free and lightweight, making KLCF efficient and easily scalable to large-scale training. Experimental results demonstrate that KLCF substantially improves factuality metrics across multiple long-form benchmarks and effectively alleviates model hallucinations.

In self-supervised reinforcement learning (RL), one of the key challenges is learning a diverse set of skills to prepare agents for unknown future tasks. Despite impressive advances, scalability and evaluation remain prevalent issues. Regarding scalability, the search for meaningful skills can be obscured by high-dimensional feature spaces, where relevant features may vary across downstream task domains. For evaluating skill diversity, defining what constitutes "diversity" typically requires a hard commitment to a specific notion of what it means for skills to be diverse, potentially leading to inconsistencies in how skill diversity is understood, making results across different approaches hard to compare, and leaving many forms of diversity unexplored. To address these issues, we adopt a measure of sample diversity that translates ideas from ecology to machine learning -- the Vendi Score -- allowing the user to specify and evaluate any desired form of diversity. We demonstrate how this metric facilitates skill evaluation and introduce VendiRL, a unified framework for learning diversely diverse sets of skills. Given distinct similarity functions, VendiRL motivates distinct forms of diversity, which could support skill-diversity pretraining in new and richly interactive environments where optimising for various forms of diversity may be desirable.

Reinforcement Learning has emerged as a dominant post-training approach to elicit agentic RAG behaviors such as search and planning from language models. Despite its success with larger models, applying RL to compact models (e.g., 0.5--1B parameters) presents unique challenges. The compact models exhibit poor initial performance, resulting in sparse rewards and unstable training. To overcome these difficulties, we propose Distillation-Guided Policy Optimization (DGPO), which employs cold-start initialization from teacher demonstrations and continuous teacher guidance during policy optimization. To understand how compact models preserve agentic behavior, we introduce Agentic RAG Capabilities (ARC), a fine-grained metric analyzing reasoning, search coordination, and response synthesis. Comprehensive experiments demonstrate that DGPO enables compact models to achieve sophisticated agentic search behaviors, even outperforming the larger teacher model in some cases. DGPO makes agentic RAG feasible in computing resource-constrained environments.

Recent progress in multi-agent systems highlights the promise of specialized agents that collaborate through a division of labor. In contrast, most tool-augmented reasoning systems still adopt a single-agent paradigm, where one large model must interleave high-level reasoning with fine-grained tool operations--a process that often leads to cognitive-load interference and unstable outputs. We propose MSARL (Multi-Small-Agent Reinforcement Learning), a novel framework that explicitly decouples reasoning from tool execution and interpretation. In MSARL, a dedicated reasoning agent focuses on strategic problem decomposition and planning, while a specialized tool agent processes long and complex tool outputs, acting as an adaptive condenser to bridge information gaps. This role-specific separation not only reduces cognitive interference but also accelerates the information flow. To enable effective collaboration, we introduce a hierarchical reinforcement learning approach that uses role-specific and collaboration-based rewards, providing granular feedback to the tool agent and a holistic, trajectory-level signal to the reasoning agent. On mathematical problem-solving with code execution, MSARL achieves more stable reasoning and higher final-answer accuracy than strong single-agent baselines.

Research on applications of reinforcement learning (RL) to large language models has mostly been focused on single-turn problems, such as mathematical reasoning or single-shot code generation. While these problems can be viewed as token-level multi-turn Markov decision processes (MDPs), this view corresponds to a degenerate case of multi-turn interaction where the environment provides no feedback. This contrasts with many real-world domains, such as software engineering (SWE), which require rich multi-turn interactions with a stateful environment that responds to each action with a non-trivial observation. To bridge this gap, we demonstrate the successful application of RL to this general regime. Our methodology begins with rejection fine-tuning (RFT) using execution feedback to train a policy to follow instructions and formatting effectively, followed by a synchronous RL pipeline using DAPO for iterative improvement. Applying this pipeline to Qwen2.5-72B-Instruct, we increase its Pass@1 on the SWE-bench Verified benchmark from 11% to 39%, substantially improving upon the 20% RFT baseline. On the May and June splits of SWE-rebench, the resulting agent achieves Pass@1 of 35% and 31% respectively, competitive with even larger models such as DeepSeek-V3-0324 or Qwen3-235B-A22B, demonstrating that our methodology offers a practical approach for training capable agents for multi-turn interactive tasks using open-weight models.

We introduce Reliable Policy Iteration (RPI) and Conservative RPI (CRPI), variants of Policy Iteration (PI) and Conservative PI (CPI), that retain tabular guarantees under function approximation. RPI uses a novel Bellman-constrained optimization for policy evaluation. We show that RPI restores the textbook \textit{monotonicity} of value estimates and that these estimates provably \textit{lower-bound} the true return; moreover, their limit partially satisfies the \textit{unprojected} Bellman equation. CRPI shares RPI's evaluation, but updates policies conservatively by maximizing a new performance-difference \textit{lower bound} that explicitly accounts for function-approximation-induced errors. CRPI inherits RPI's guarantees and, crucially, admits per-step improvement bounds. In initial simulations, RPI and CRPI outperform PI and its variants. Our work addresses a foundational gap in RL: popular algorithms such as TRPO and PPO derive from tabular CPI yet are deployed with function approximation, where CPI's guarantees often fail-leading to divergence, oscillations, or convergence to suboptimal policies. By restoring PI/CPI-style guarantees for \textit{arbitrary} function classes, RPI and CRPI provide a principled basis for next-generation RL.

Deep multi-agent reinforcement learning (MARL) has been demonstrated effectively in simulations for multi-robot problems. For autonomous vehicles, the development of vehicle-to-vehicle (V2V) communication technologies provide opportunities to further enhance system safety. However, zero-shot transfer of simulator-trained MARL policies to dynamic hardware systems remains challenging, and how to leverage communication and shared information for MARL has limited demonstrations on hardware. This problem is challenged by discrepancies between simulated and physical states, system state and model uncertainties, practical shared information design, and the need for safety guarantees in both simulation and hardware. This paper designs RSR-RSMARL, a novel Robust and Safe MARL framework that supports Real-Sim-Real (RSR) policy adaptation for multi-agent systems with communication among agents, with both simulation and hardware demonstrations. RSR-RSMARL leverages state (includes shared state information among agents) and action representations considering real system complexities for MARL formulation. The MARL policy is trained with robust MARL algorithm to enable zero-shot transfer to hardware considering the sim-to-real gap. A safety shield module using Control Barrier Functions (CBFs) provides safety guarantee for each individual agent. Experimental results on 1/10th-scale autonomous vehicles with V2V communication demonstrate the ability of RSR-RSMARL framework to enhance driving safety and coordination across multiple configurations. These findings emphasize the importance of jointly designing robust policy representations and modular safety architectures to enable scalable, generalizable RSR transfer in multi-agent autonomy.

Diffusion-based generative models are emerging as powerful tools for long-horizon planning in reinforcement learning (RL), particularly with offline datasets. However, their performance is fundamentally limited by the quality and diversity of training data. This often restricts their generalization to tasks outside their training distribution or longer planning horizons. To overcome this challenge, we propose State-Covering Trajectory Stitching (SCoTS), a novel reward-free trajectory augmentation method that incrementally stitches together short trajectory segments, systematically generating diverse and extended trajectories. SCoTS first learns a temporal distance-preserving latent representation that captures the underlying temporal structure of the environment, then iteratively stitches trajectory segments guided by directional exploration and novelty to effectively cover and expand this latent space. We demonstrate that SCoTS significantly improves the performance and generalization capabilities of diffusion planners on offline goal-conditioned benchmarks requiring stitching and long-horizon reasoning. Furthermore, augmented trajectories generated by SCoTS significantly improve the performance of widely used offline goal-conditioned RL algorithms across diverse environments.