The paper introduces Adaptive Policy-Guided Error Mitigation (APGEM), a context-aware layer that dynamically selects error mitigation strategies—such as ZNE, PEC, CDR, and REM—during quantum reinforcement learning (QRL) training on NISQ devices. APGEM uses policy-level indicators (quantum-state fidelity, policy entropy, cumulative reward, and approximation ratio) to choose the most suitable mitigation method and integrates it directly into the reinforcement learning loop. Evaluated on the Capacitated Vehicle Routing Problem under various NISQ noise models, APGEM outperforms static mitigation techniques, achieving about 94% of an oracle strategy’s utility, maintaining higher fidelity as noise increases, and producing more stable learning behavior.
By Bisma Majid, Shabir Ahmed Sofi, Mir Mohammad Yousuf
The paper introduces Commute-Time-Preserving World Models (CTWMs), which learn latent representations that reflect commute-times in an environment by using a latent displacement predictor and a log-determinant regularizer. This approach addresses the issue that existing self-supervised methods degrade the necessary eigenvalue-dependent scaling for accurate commute-time representation. In experiments, CTWMs outperform the task-agnostic baseline LeWM on several continuous goal-reaching benchmarks while using only half the parameters.
By Michael Hauri, Peter Buttaroni, Fabian A. Mikulasch, Friedemann Zenke
SkillEvoLean introduces a mutation‑enhanced skill evolution framework for Lean theorem provers, jointly refining a high‑level solving policy and its reference knowledge. The method combines progressive updates from successful and failed proof trajectories with mutation‑based exploration when no complete proof is found, sampling mathematical concepts to generate new skill candidates. Evaluations on MiniF2F, PutnamBench, IMO 2025, and USAMO 2026 show significant proof success improvements over baseline approaches.
By Kuo Zhou, ZiXion Yang, Lu Zhang
The paper introduces Forward CIP (F‑CIP), an RL‑native formulation of the Controllable Information Production objective that relies solely on system dynamics, eliminating the need for domain‑specific information variable selection. F‑CIP is proven compatible with reinforcement learning and, when applied to existing algorithms, enables agents to autonomously discover primitive behaviors such as balancing and maintaining controllability. Coupled with a simple forward‑velocity reward, the method yields coordinated gaits like hopping and running without reward engineering.
By Tristan Shah, Wooyoung Chung, Volodomyr Makarenko, Juan Wachs, Stas Tiomkin
MASkillBlender is a multi-agent reinforcement learning framework that enables decentralized coordination of multiple humanoid robots for loco-manipulation tasks. It learns a shared high-level policy that blends pre-trained single-humanoid skills, requiring only task-level rewards and no task-specific motion references. The approach includes a permutation-based data augmentation technique that preserves policy-gradient direction, and it has been evaluated on several coordination tasks across two humanoid embodiments, consistently achieving strong performance.
By Yifan Hu, Luhang Hong, Mingkang Long, Danning Wang, Chengfeng Jia, Rong Su, Junjie Fu, Guanghui Wen
The paper introduces LLMLeak, a covert exfiltration technique that exploits Large‑Language‑Model (LLM) web‑fetching capabilities to transmit confidential data. By embedding a secret into a URL and presenting the corresponding website as part of a legitimate task, the malicious client tricks the LLM into fetching the URL, thereby leaking the secret to an attacker‑controlled server. Experiments on eleven open‑parameter models show a 79.7% success rate, and a real‑world case study confirms the attack’s practicality.
By Alessandro Pegoraro, Daryan Merx, Phillip Rieger, Ahmad-Reza Sadeghi
LumoTree is a verifier designed for hybrid language models that ensures a single coherent continuation across recurrent, convolution, and attention states. It executes recurrent paths in parallel, reuses state tiles, and coordinates replay, history gathering, and cache remapping through a shared logical tree. Experiments demonstrate exact candidate‑selection parity and recurrent agreement within error bounds, and a Qwen3.8‑27B deployment achieved 25.63 pooled tokens/s on a single NVIDIA DGX Spark.
By Zhiyuan Ma
arXiv:2610. 00256v1 Announce Type: new Abstract: External verification can correct individual outputs while leaving a self-reinforcing population in the basin of a wrong consensus.
By Shivam Gupta
The paper investigates a phenomenon called forking, a type of generalization failure observed in NanoGPT and similar autoregressive models. Forking manifests as a sharp divergence between training and validation loss at epoch boundaries, especially when models employ over‑encoding n‑gram memory modules and data replay. The authors reproduce the effect in both vanilla NanoGPT and a DeepSeek-style model, attributing it to repeated updates that sharpen seen continuations while suppressing unseen ones, with low‑frequency contexts contributing most to the loss gap.
By Shanbin Yu, Shaoyang Guo, Haoran Zhao, Danni Yu, Ziming Liu
MECHVAR is a lightweight, auditable rule for selecting experiments from a finite library to discriminate between candidate mechanisms. It chooses probes by maximizing the posterior‑weighted variance of predicted responses, a score that aligns with the Box–Hill pairwise‑KL criterion and links to expected information gain when separations are small. Experiments on a 25‑block audit and a Digits loop show MECHVAR outperforming confirmation‑first strategies and matching or exceeding EIG in identification accuracy while being far faster to compute.
By Yifan Guo
The paper introduces PRISMS, a framework that uses expert pairwise rankings of varying fidelity to curate scientific designs without relying on data-intensive regression models. By escalating queries from lower- to higher-fidelity rankers based on Fisher-information, PRISMS improves discovery recall and reduces the number of screening rounds compared to regression-only and non‑escalated ranking methods. In optimization tasks, PRISMS outperforms Bayesian optimization by achieving higher hypervolume.
By Kevin Tirta Wijaya, Alston Lo, Michael Sun, Wojciech Matusik, Vahid Babaei
The paper investigates when intrinsic rewards effectively drive exploration in reinforcement learning. It introduces a formal criterion that evaluates policies based on the counterfactual information they acquire, comparing how well their histories can replace experience from alternative policies. Using a simple environment, the authors show that common intrinsic reward objectives—count-based, prediction-error, empowerment, and information-gain—can lead to Pareto-suboptimal exploration under this criterion, and they propose conditions and a new objective that better align with optimal exploration.
By Scott W. Viteri (Stanford University), Laura Gomezjurado Gonzalez (Stanford University), Clark Barrett (Stanford University)
The paper investigates how reinforcement learning agents trained in one cyber simulation can be transferred to other simulators or real environments. It introduces a framework that decouples state alignment from action translation, allowing zero‑shot policy transfer without retraining. Experiments across four cyber platforms show that transferred policies can preserve performance in closely aligned settings and achieve substantial win rates in more divergent environments.
By Sabrina Saika, Yinuo Du, Aritran Piplai
TRACE tackles real‑world dynamic resource assignment by combining evolutionary automatic heuristic design with an agentic knowledge‑extraction workflow. A Reasoner agent interprets system logs to hypothesize about underlying dynamics, while a Coder agent generates and runs schema‑specific code to validate these hypotheses, producing insights or executable tools for the evolved heuristics. Evaluations on a synthetic cloud benchmark and a 5G vRAN scenario show that TRACE outperforms existing AHD methods, delivering more auditable heuristics with less than 2% overhead.
By Jose A. Ayala-Romero, Andres Garcia-Saavedra, Xavier Costa-Perez
The paper compares distributed adversarial training algorithms—both centralized and decentralized—within multi‑agent learning environments. It introduces a theoretical framework to analyze how efficiently these algorithms escape local minima, a property linked to model flatness and robustness. The study finds that with small perturbation bounds and large batch sizes, decentralized methods (consensus and diffusion) escape local minima faster than centralized ones, but this advantage may diminish as attack strength increases.
By Ying Cao, Kun Yuan, Ali H. Sayed
JEPA-Bisim introduces a bisimulation encoder to joint-embedding predictive world models, ensuring that states with similar transition dynamics are mapped to nearby latent representations while suppressing irrelevant slow features such as background changes and distractors. The approach improves robustness on navigation (PointMaze) and manipulation (PushT) tasks under varied test-time visual conditions, achieving up to tenfold smaller latent spaces than DINO-WM. It remains effective across different pre-trained visual encoders, including DINOv2, SimDINOv2, and iBOT.
By Leonardo F. Toso, Davit Shadunts, Yunyang Lu, Gloria Geng, Nihal Sharma, Donglin Zhan, Nam H. Nguyen, James Anderson
The paper introduces the Alignment Flywheel, a governance‑centric hybrid multi‑agent system (MAS) that separates decision generation from safety governance. It defines a Proposer that generates candidate trajectories, a Safety Oracle stack that evaluates safety, and an Enforcement layer that applies risk policies at runtime. A governance MAS oversees monitoring, red‑teaming, verification, and versioned release management, enabling patch‑local fixes to safety failures without retraining the Proposer. The architecture is implementation‑agnostic and is demonstrated in two scenarios: a learned spatial Oracle and a clinical GenAI proxy. The authors provide open‑source code at https://github.com/decide-ugent/Alignment-Flywheel.
By Elias Malomgr\'e, Pieter Simoens
The paper proposes a multi‑objective framework that integrates reinforcement learning‑based multiple instance learning (RL‑MIL), adversarial debiasing, and preference‑conditioned hypernetworks to predict student performance while addressing fairness concerns. Each student is represented as a bag of weakly labeled interactions, and an RL agent selects informative instances for classification. Although the baseline RL‑MIL achieves strong accuracy, the hypernetwork extensions fail to produce a smooth trade‑off between predictive performance and Equalized Odds due to mode collapse, objective dominance, and weak gradient propagation, indicating that additional mechanisms are needed for stable, fair RL‑MIL systems.
By Bente Hinkenhuis, Seyed Sahand Mohammadi Ziabari, Ali Mohammed Mansoor Alsahag
JEPA‑TTT is a method that continuously adapts the latent dynamics predictor of a pretrained Joint‑Embedding Predictive Architecture (JEPA) world model during test time. It performs self‑supervised updates across episodes while keeping the visual encoder and reward head fixed, using dense replay to sample prediction windows from a growing buffer. In experiments on eight dynamics shifts across four continuous‑control environments, JEPA‑TTT reduces latent prediction error by 83% and improves planning performance by 153% compared to the frozen model.
By Zheyuan Zhang, Suyu Ye, Nakul Agarwal, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Daniel Khashabi, Tianmin Shu, Vaishnav Tadiparthi
The paper introduces a reliability‑aware short‑term roll prediction framework for unmanned surface vehicles (USVs) that combines a multi‑task learning architecture with an adaptive centralization strategy. The model uses a shared backbone to feed a regression head for precise roll prediction and a quantification head for confidence scoring, enabling accurate predictions alongside reliability estimates. Experiments on a real‑sea dataset show that the approach effectively quantifies prediction reliability and generalizes well across varying operational conditions.
By Kaizhen Li, Xi Zhou, Zihao Wang, Dan Zhang, Jianjian Liu, Xiaowei Li