Frontis-MA1: Training an AI4AI Model towards Recursive Self-Improvement in Machine Learning Engineering

Recursive self-improvement (RSI) requires AI systems that improve the process of building AI (i.e., AI4AI); machine learning engineering (MLE) offers a concrete, executable testbed for studying this capability. We introduce OpenMLE, an open full-stack system for RSI research in MLE, spanning verifiable task environments with execution feedback (OpenMLE-Gym), operator learning (OpenMLE-RL), and long-horizon search (OpenMLE-Evo). On this stack we post-train Frontis-MA1 (35B) as a meta-evolution agent for MLE, aligning post-training and inference around four atomic program-evolution operators (Draft, Improve, Debug, Crossover): the same operators are trained via execution-grounded SFT and RL on data deduplicated against all evaluation benchmarks, then composed into long-horizon search, coupling learning and evolution in a single loop. On MLE-Bench Lite under a 12-hour per-task budget on one RTX 4090 capped at 12 GB VRAM, Frontis-MA1 (35B) improves Medal Average from 39.39% to 60.61% over its base model with OpenMLE-Evo, and reaches 71.21% with OpenMLE-Evo-Max (benchmark-independent experience priors and asynchronous search), exceeding GPT-5.5 + Codex and approaching GPT-5.6 Sol and the 2.8T Kimi K3. On held-out NatureBench Lite, both components transfer: with the framework fixed, swapping in the trained model raises Match-SOTA from 50% to 70%; with the model fixed, swapping in OpenMLE-Evo raises it from 20% to 50%. We release the model weights and the full OpenMLE stack to enable reproducible research on executable AI4AI toward RSI. Code: https://github.com/FrontisAI/OpenRSI

SinD 2.0: A Multi-City UAV Dataset with Semantic Risk Annotations for SOTIF-Oriented Safety Validation at Signalized Intersections

Safety validation at signalized intersections remains a critical bottleneck for the deployment of autonomous driving systems (ADS), as these scenarios involve dense heterogeneous traffic, contested right of way, and long-tail safety-critical interactions, posing significant challenges to the Safety of the Intended Functionality (SOTIF). Existing naturalistic driving datasets often suffer from geographical homogeneity, sparsity of safety-critical events, and lack of semantic risk annotations, which limit the evaluation of algorithmic generalizability and targeted SOTIF verification. To address these gaps, this paper introduces SinD 2.0, a large-scale drone-based intersection dataset dedicated to cross-domain ADS safety analysis. The main contributions of SinD 2.0 are: (1) Cross-domain diversity: It covers six signalized intersections across four Chinese cities, capturing distinct intersection topologies and regional driving behavior characteristics; (2) High-density risk interactions: A total of 32,682 safety-critical events are extracted via surrogate safety measures, significantly enriching the density of boundary test scenarios; (3) Hierarchical semantic annotations: Besides integration with high-definition (HD) maps and Signal Phase and Timing (SPaT) data, it provides multi-dimensional semantic labels including traffic violations, high-risk interactions, visual shielding, and narrow feasible areas; (4) Full-stack testing toolchain: It supports automated scenario extraction, prediction-only evaluation, open-loop replay, reactive closed-loop testing, and photorealistic rendering. Benchmark experiments demonstrate that SinD 2.0 exhibits significant domain shifts across cities, and the semantic risk subsets can effectively expose the performance limitations of ADS algorithms. The dataset, annotations, and testing toolchain are available at https://github.com/SOTIF-AVLab/SinD/tree/main.

AssetGen: Deployable 3D Asset Generation at Interactive Speed

While 3D generation is progressing rapidly, recent work has often focused on obtaining high-resolution assets, leaving user experience and deployability as afterthoughts. We present AssetGen, a 3D generator that focuses instead on these two aspects. Given one reference image, in 30 seconds it produces a high-quality mesh with baked normals, a color texture, and a controlled polygon budget suitable for real-time rendering, including mobile use cases. The AssetGen Flash variant further reduces latency to 14 seconds for interactive and agentic creation loops. Our model generates the object geometry with a coarse-to-refine VecSet framework, which implements mesh simplification, cleaning, and normal baking on the GPU, and a fast parallel UV unwrapping. It then generates textures in a multi-view fashion, followed by backprojection and 3D inpainting. Model distillation, kernel optimization, and pipeline parallelization are co-designed to accelerate the system end-to-end. We introduce numerous automated and blind human evaluations and demonstrate competitive visual quality against leading commercial solutions in 30 seconds and preview-quality results in less than 15 seconds. The final result is a system that supports AI-assisted, deployable 3D content creation in interactive workflows.

Post-Trained MoE Can Skip Half Experts via Self-Distillation

Mixture-of-Experts (MoE) scales language models efficiently through sparse expert activation, and its dynamic variant further reduces computation by adjusting the activated experts in an input-dependent manner. Existing dynamic MoE methods usually rely on pre-training from scratch or task-specific adaptation, leaving the practical conversion of fully trained MoE underexplored. Enabling such adaptation would directly alleviate the inference costs by allowing easy tokens to bypass unnecessary expert during serving. This paper introduces Zero-Expert Self-Distillation Adaptation (ZEDA), a low-cost framework that transforms post-trained static MoE models into efficient dynamic ones. To stabilize this architectural conversion, ZEDA injects parameter-free zero-output experts into each MoE layer and adapts the augmented model through two-stage self-distillation, utilizing the original MoE as a frozen teacher and applying a group-level balancing loss. On Qwen3-30B-A3B and GLM-4.7-Flash across 11 benchmarks spanning math, code, and instruction following, ZEDA eliminates over 50% of expert FLOPs at marginal accuracy loss. It outperforms the strongest dynamic MoE baseline by 6.1 and 4.0 points on the two models, and delivers ~1.20$\times$ end-to-end inference speedup.

Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling

Recent progress in reasoning models has substantially advanced long-horizon mathematical and scientific problem solving, with several systems now reaching gold-medal-level performance on International Mathematical Olympiad (IMO) and International Physics Olympiad (IPhO) problems. In this paper, we introduce a simple and unified recipe for converting a post-trained reasoning backbone into a rigorous olympiad-level solver. The recipe first uses a reverse-perplexity curriculum for SFT to instill rigorous proof-search and self-checking behaviors, then scales these behaviors through a two-stage RL pipeline that progresses from RL with verifiable rewards to more delicate proof-level RL, and finally boosts solving performance with test-time scaling. Applying this recipe, we train a 30B-A3B backbone with SFT on around 340K sub-8K-token trajectories followed by 200 RL steps. The resulting model, SU-01, supports stable reasoning on difficult problems with trajectories exceeding 100K tokens, while achieving gold-medal-level performance on mathematical and physical olympiad competitions, including IMO 2025/USAMO 2026 and IPhO 2024/2025. It also demonstrates strong generalization of scientific reasoning to domains beyond mathematics and physics.

Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning

Tool-integrated reasoning (TIR) offers a direct way to extend thinking models beyond the limits of text-only reasoning. Paradoxically, we observe that tool-enabled evaluation can degrade reasoning performance even when the strong thinking models make almost no actual tool calls. In this paper, we investigate how to inject natural tool-use behavior into a strong thinking model without sacrificing its no-tool reasoning ability, and present a comprehensive TIR recipe. We highlight that (i) the effectiveness of TIR supervised fine-tuning (SFT) hinges on the learnability of teacher trajectories, which should prioritize problems inherently suited for tool-augmented solutions; (ii) controlling the proportion of tool-use trajectories could mitigate the catastrophic forgetting of text-only reasoning capacity; (iii) optimizing for pass@k and response length instead of training loss could maximize TIR SFT gains while preserving headroom for reinforcement learning (RL) exploration; (iv) a stable RL with verifiable rewards (RLVR) stage, built upon suitable SFT initialization and explicit safeguards against mode collapse, provides a simple yet remarkably effective solution. When applied to Qwen3 thinking models at 4B and 30B scales, our recipe yields models that achieve state-of-the-art performance in a wide range of benchmarks among open-source models, such as 96.7% and 99.2% on AIME 2025 for 4B and 30B, respectively.

Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents

When an LLM-based agent improves on a task, is the gain from the model itself or from the reasoning paradigm wrapped around it? We study this question by comparing six inference-time paradigms, namely Direct, CoT, ReAct, Plan-Execute, Reflection, and ReCode, across four frontier LLMs and ten benchmarks, yielding roughly 18,000 runs. We find that reasoning structure helps dramatically on some tasks but hurts on others: ReAct improves over Direct by 44pp on GAIA, while CoT degrades performance by 15pp on HumanEval. No single paradigm dominates, and oracle per-task selection beats the best fixed paradigm by 17.1pp on average. Motivated by this complementarity, we propose a select-then-solve approach: before answering each task, a lightweight embedding-based router selects the most suitable paradigm. Across four models, the router improves average accuracy from 47.6% to 53.1%, outperforming the best fixed paradigm at 50.3% by 2.8pp and recovering up to 37% of the oracle gap. In contrast, zero-shot self-routing only works for GPT-5 at 67.1% and fails for weaker models, all trailing the learned router. Our results argue that reasoning paradigm selection should be a per-task decision made by a learned router, not a fixed architectural choice.

Ego to World: Collaborative Spatial Reasoning in Embodied Systems via Reinforcement Learning

Understanding the world from distributed, partial viewpoints is a fundamental challenge for embodied multi-agent systems. Each agent perceives the environment through an ego-centric view that is often limited by occlusion and ambiguity. To study this problem, we introduce the Ego-to-World (E2W) benchmark, which evaluates a vision-language model's ability to fuse heterogeneous viewpoints across three tasks: (i) global counting, (ii) relational location reasoning, and (iii) action-oriented grasping that requires predicting view-specific image coordinates. To address this setting, we propose CoRL, a two-stage framework that combines Chain-of-Thought supervised fine-tuning with reinforcement learning using Group-Relative Policy Optimization. Its core component, the Cross-View Spatial Reward (CVSR), provides dense task-aligned feedback by linking reasoning steps to visual evidence, ensuring coherent cross-view entity resolution, and guiding the model toward correct final predictions. Experiments on E2W show that CoRL consistently surpasses strong proprietary and open-source baselines on both reasoning and perception-grounding metrics, while ablations further confirm the necessity of each CVSR component. Beyond that, CoRL generalizes to external spatial reasoning benchmarks and enables effective real-world multi-robot manipulation with calibrated multi-camera rigs, demonstrating cross-view localization and successful grasp-and-place execution. Together, E2W and CoRL provide a principled foundation for learning world-centric scene understanding from distributed, ego-centric observations, advancing collaborative embodied AI.

Reading $ eq$ Seeing: Diagnosing and Closing the Typography Gap in Vision-Language Models

Vision-Language Models achieve near-perfect accuracy at reading text in images, yet prove largely typography-blind: capable of recognizing what text says, but not how it looks. We systematically investigate this gap by evaluating font family, size, style, and color recognition across 26 fonts, four scripts, and three difficulty levels. Our evaluation of 15 state-of-the-art VLMs reveals a striking perception hierarchy: color recognition is near-perfect, yet font style detection remains universally poor. We further find that model scale fails to predict performance and that accuracy is uniform across difficulty levels, together pointing to a training-data omission rather than a capacity ceiling. LoRA fine-tuning on a small set of synthetic samples substantially improves an open-source model, narrowing the gap to the best closed-source system and surpassing it on font size recognition. Font style alone remains resistant to fine-tuning, suggesting that relational visual reasoning may require architectural innovation beyond current patch-based encoders. We release our evaluation framework, data, and fine-tuning recipe to support progress in closing the typographic gap in vision-language understanding.

How Far Can Unsupervised RLVR Scale LLM Training?

Unsupervised reinforcement learning with verifiable rewards (URLVR) offers a pathway to scale LLM training beyond the supervision bottleneck by deriving rewards without ground truth labels. Recent works leverage model intrinsic signals, showing promising early gains, yet their potential and limitations remain unclear. In this work, we revisit URLVR and provide a comprehensive analysis spanning taxonomy, theory and extensive experiments. We first classify URLVR methods into intrinsic versus external based on reward sources, then establish a unified theoretical framework revealing that all intrinsic methods converge toward sharpening the model's initial distribution This sharpening mechanism succeeds when initial confidence aligns with correctness but fails catastrophically when misaligned. Through systematic experiments, we show intrinsic rewards consistently follow a rise-then-fall pattern across methods, with collapse timing determined by model prior rather than engineering choices. Despite these scaling limits, we find intrinsic rewards remain valuable in test-time training on small datasets, and propose Model Collapse Step to measure model prior, serving as a practical indicator for RL trainability. Finally, we explore external reward methods that ground verification in computational asymmetries, showing preliminary evidence they may escape the confidence-correctness ceiling. Our findings chart boundaries for intrinsic URLVR while motivating paths toward scalable alternatives.