Training and evaluation of Reinforcement Learning (RL) web agents have gained increasing attention, yet a scalable and efficient environment that couples realistic and robust browser-side interaction with controllable server-side state at scale is still missing. Existing environments tend to have one or more of the following issues: they overwhelm policy models with excessive and noisy context; they perform actions non-deterministically without waiting for the UI or network to stabilize; or they cannot scale isolated client-server containers effectively for parallel RL rollouts. We propose WEBSERV, an environment that includes 1) a compact, site-agnostic browser environment that balances context and action complexity, and 2) a scalable RL environment via efficient launching and resetting web-servers to enable scalable RL training and evaluation. We evaluate WEBSERV on the shopping CMS and Gitlab tasks in WebArena, achieving state-of-the-art single-prompt success rates while cutting launch latency by ~5x and storage need by ~240x, with a comparable memory footprint, enabling 200+ concurrent containers on a single host.

Reinforcement learning (RL) has experienced a second wind in the past decade. While incredibly successful in images and videos, these systems still operate within the realm of propositional tasks ignoring the inherent structure that exists in the problem. Consequently, relational extensions (RRL) have been developed for such structured problems that allow for effective generalization to arbitrary number of objects. However, they inherently make strong assumptions about the problem structure. We introduce a novel framework that combines RRL with object-centric representation to handle both structured and unstructured data. We enhance learning by allowing the system to actively query the human expert for guidance by explicitly modeling the uncertainty over the policy. Our empirical evaluation demonstrates the effectiveness and efficiency of our proposed approach.

Reinforcement Learning frameworks, particularly those utilizing human annotations, have become an increasingly popular method for preference fine-tuning, where the outputs of a language model are tuned to match a certain set of behavioral policies or guidelines. Reinforcement Learning through Human Feedback (RLHF) is perhaps the most popular implementation of such a framework, particularly for aligning LMs toward safety and human intent. However, the internal workings of how such alignment is achieved remain largely opaque. In this work, we systematically analyze preference optimization for language model alignment by applying layer-wide causal patching between a base model and its tuned counterpart across human preference pairs. We implement our methodology on \textit{Llama-3.2-1B}, and find that alignment is spatially localized: mid-layer activations encode a distinct subspace that causally determines reward-consistent behavior, while early and late layers remain largely unaffected. Utilizing LASSO regression, we also find that only a small number of layers possess non-zero coefficients linking activation distances to reward gains. Overall, we show that, at least for some language models, alignment from human-based, preferential tuning is a directional, low rank process, rather than diffuse and parameteric.

When users submit queries to Large Language Models (LLMs), their prompts can often contain sensitive data, forcing a difficult choice: Send the query to a powerful proprietary LLM providers to achieving state-of-the-art performance and risk data exposure, or relying on smaller, local models guarantees data privacy but often results in a degradation of task performance. Prior approaches have relied on static pipelines that use LLM rewriting, which shatters linguistic coherence and indiscriminately removes privacy-sensitive information, including task-critical content. We reformulate this challenge (Privacy-Conscious Delegation) as a sequential decision-making problem and introduce a novel reinforcement learning (RL) framework called PrivacyPAD to solve it. Our framework trains an agent to dynamically route text chunks, learning a policy that optimally balances the trade-off between privacy leakage and task performance. It implicitly distinguishes between replaceable Personally Identifiable Information (PII) (which it shields locally) and task-critical PII (which it strategically sends to the remote model for maximal utility). To validate our approach in complex scenarios, we also introduce a new medical dataset with high PII density. Our framework achieves a new state-of-the-art on the privacy-utility frontier, demonstrating the necessity of learned, adaptive policies for deploying LLMs in sensitive environments.

Social networks have become a crucial source of real-time information for individuals. The influence of social bots within these platforms has garnered considerable attention from researchers, leading to the development of numerous detection technologies. However, the vulnerability and robustness of these detection methods is still underexplored. Existing Graph Neural Network (GNN)-based methods cannot be directly applied due to the issues of limited control over social agents, the black-box nature of bot detectors, and the heterogeneity of bots. To address these challenges, this paper proposes the first adversarial multi-agent Reinforcement learning framework for social Bot control attacks (RoBCtrl) targeting GNN-based social bot detectors. Specifically, we use a diffusion model to generate high-fidelity bot accounts by reconstructing existing account data with minor modifications, thereby evading detection on social platforms. To the best of our knowledge, this is the first application of diffusion models to mimic the behavior of evolving social bots effectively. We then employ a Multi-Agent Reinforcement Learning (MARL) method to simulate bots adversarial behavior. We categorize social accounts based on their influence and budget. Different agents are then employed to control bot accounts across various categories, optimizing the attachment strategy through reinforcement learning. Additionally, a hierarchical state abstraction based on structural entropy is designed to accelerate the reinforcement learning. Extensive experiments on social bot detection datasets demonstrate that our framework can effectively undermine the performance of GNN-based detectors.

One of the major problems in Machine Learning (ML) and Artificial Intelligence (AI) is the fact that the probability distribution of the test data in the real world could deviate substantially from the probability distribution of the training data set. When this happens, the predictions of an ML system or an AI agent could involve large errors which is very troublesome and undesirable. While this is a well-known hard problem plaguing the AI and ML systems' accuracy and reliability, in certain applications such errors could be critical for safety and reliability of AI and ML systems. One approach to deal with this problem is to monitor and measure the deviation in the probability distribution of the test data in real time and to compensate for this deviation. In this paper, we propose and explore the use of Kolmogorov-Smirnov (KS) Test for measuring the distribution shift and we show how the KS distance can be used to quantify the distribution shift and its impact on an AI agent's performance. Our results suggest that KS distance could be used as a valuable statistical tool for monitoring and measuring the distribution shift. More specifically, it is shown that even a distance of KS=0.02 could lead to about 50\% increase in the travel time at a single intersection using a Reinforcement Learning agent which is quite significant. It is hoped that the use of KS Test and KS distance in AI-based smart transportation could be an important step forward for gauging the performance degradation of an AI agent in real time and this, in turn, could help the AI agent to cope with the distribution shift in a more informed manner.

Traditional stochastic control methods in finance struggle in real world markets due to their reliance on simplifying assumptions and stylized frameworks. Such methods typically perform well in specific, well defined environments but yield suboptimal results in changed, non stationary ones. We introduce FinFlowRL, a novel framework for financial optimal stochastic control. The framework pretrains an adaptive meta policy learning from multiple expert strategies, then finetunes through reinforcement learning in the noise space to optimize the generative process. By employing action chunking generating action sequences rather than single decisions, it addresses the non Markovian nature of markets. FinFlowRL consistently outperforms individually optimized experts across diverse market conditions.

Building effective knowledge graphs (KGs) for Retrieval-Augmented Generation (RAG) is pivotal for advancing question answering (QA) systems. However, its effectiveness is hindered by a fundamental disconnect: the knowledge graph (KG) construction process is decoupled from its downstream application, yielding suboptimal graph structures. To bridge this gap, we introduce AutoGraph-R1, the first framework to directly optimize KG construction for task performance using Reinforcement Learning (RL). AutoGraph-R1 trains an LLM constructor by framing graph generation as a policy learning problem, where the reward is derived from the graph's functional utility in a RAG pipeline. We design two novel, task-aware reward functions, one for graphs as knowledge carriers and another as knowledge indices. Across multiple QA benchmarks, AutoGraph-R1 consistently enables graph RAG methods to achieve significant performance gains over using task-agnostic baseline graphs. Our work shows it is possible to close the loop between construction and application, shifting the paradigm from building intrinsically ``good'' graphs to building demonstrably ``useful'' ones.

Humans excel at bimanual assembly tasks by adapting to rich tactile feedback -- a capability that remains difficult to replicate in robots through behavioral cloning alone, due to the suboptimality and limited diversity of human demonstrations. In this work, we present VT-Refine, a visuo-tactile policy learning framework that combines real-world demonstrations, high-fidelity tactile simulation, and reinforcement learning to tackle precise, contact-rich bimanual assembly. We begin by training a diffusion policy on a small set of demonstrations using synchronized visual and tactile inputs. This policy is then transferred to a simulated digital twin equipped with simulated tactile sensors and further refined via large-scale reinforcement learning to enhance robustness and generalization. To enable accurate sim-to-real transfer, we leverage high-resolution piezoresistive tactile sensors that provide normal force signals and can be realistically modeled in parallel using GPU-accelerated simulation. Experimental results show that VT-Refine improves assembly performance in both simulation and the real world by increasing data diversity and enabling more effective policy fine-tuning. Our project page is available at https://binghao-huang.github.io/vt_refine/.

Scaling reinforcement learning (RL) often requires running environments across many machines, but most frameworks tie simulation, training, and infrastructure into rigid systems. We introduce ClusterEnv, a lightweight interface for distributed environment execution that preserves the familiar Gymnasium API. ClusterEnv uses the DETACH pattern, which moves environment reset() and step() operations to remote workers while keeping learning centralized. To reduce policy staleness without heavy communication, we propose Adaptive Policy Synchronization (APS), where workers request updates only when divergence from the central learner grows too large. ClusterEnv supports both on- and off-policy methods, integrates into existing training code with minimal changes, and runs efficiently on clusters. Experiments on discrete control tasks show that APS maintains performance while cutting synchronization overhead. Source code is available at https://github.com/rodlaf/ClusterEnv.