arXiv:2602.19416v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) enables powerful LLM alignment but can introduce reward hacking - models exploit spurious correlations in proxy rewards without genuine alignment. Compounding this, the objectives internalized during RLHF remain opaque, making hacking behaviors difficult to detect or correct. We introduce IR3 (Interpretable Reward Reconstruction and Rectification), a framework that reverse-engineers, interprets, and surgically repairs the implicit objectives driving RLHF-tuned models. We propose Contrastive Inverse Reinforcement Learning (C-IRL), which reconstructs the implicit reward function by contrasting paired responses from post-alignment and baseline policies to explain behavioral shifts during RLHF. We then decompose the reconstructed reward via sparse autoencoders into interpretable features, enabling identification of hacking signatures through contribution analysis. Finally, we propose mitigation strategies - clean reward optimization, adversarial shaping, constrained optimization, and feature-guided distillation - that target problematic features while preserving beneficial alignment. Experiments across multiple reward model configurations show that IR3 achieves 0.89 correlation with ground-truth rewards, identifies hacking features with over 90% precision, and significantly reduces hacking behaviors while maintaining capabilities within 3% of the original model.

arXiv:2510.18316v2 Announce Type: replace-cross Abstract: Imitation learning from large-scale, diverse human demonstrations has been shown to be effective for training robots, but collecting such data is costly and time-consuming. This challenge intensifies for multi-step bimanual mobile manipulation, where humans must teleoperate both the mobile base and two high-DoF arms. Prior X-Gen works have developed automated data generation frameworks for static (bimanual) manipulation tasks, augmenting a few human demos in simulation with novel scene configurations to synthesize large-scale datasets. However, prior works fall short for bimanual mobile manipulation tasks for two major reasons: 1) a mobile base introduces the problem of how to place the robot base to enable downstream manipulation (reachability) and 2) an active camera introduces the problem of how to position the camera to generate data for a visuomotor policy (visibility). To address these challenges, MoMaGen formulates data generation as a constrained optimization problem that satisfies hard constraints (e.g., reachability) while balancing soft constraints (e.g., visibility while navigation). This formulation generalizes across most existing automated data generation approaches and offers a principled foundation for developing future methods. We evaluate on four multi-step bimanual mobile manipulation tasks and find that MoMaGen enables the generation of much more diverse datasets than previous methods. As a result of the dataset diversity, we also show that the data generated by MoMaGen can be used to train successful imitation learning policies using a single source demo. Furthermore, the trained policy can be fine-tuned with a very small amount of real-world data (40 demos) to be succesfully deployed on real robotic hardware. More details are on our project page: momagen.github.io.

arXiv:2602.10604v2 Announce Type: replace-cross Abstract: We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency. We focus on what matters most when building agents: sharp reasoning and fast, reliable execution. Step 3.5 Flash pairs a 196B-parameter foundation with 11B active parameters for efficient inference. It is optimized with interleaved 3:1 sliding-window/full attention and Multi-Token Prediction (MTP-3) to reduce the latency and cost of multi-round agentic interactions. To reach frontier-level intelligence, we design a scalable reinforcement learning framework that combines verifiable signals with preference feedback, while remaining stable under large-scale off-policy training, enabling consistent self-improvement across mathematics, code, and tool use. Step 3.5 Flash demonstrates strong performance across agent, coding, and math tasks, achieving 85.4% on IMO-AnswerBench, 86.4% on LiveCodeBench-v6 (2024.08-2025.05), 88.2% on tau2-Bench, 69.0% on BrowseComp (with context management), and 51.0% on Terminal-Bench 2.0, comparable to frontier models such as GPT-5.2 xHigh and Gemini 3.0 Pro. By redefining the efficiency frontier, Step 3.5 Flash provides a high-density foundation for deploying sophisticated agents in real-world industrial environments.