Multimodal Reinforcement Learning with Agentic Verifier for AI Agentscs.AI updates on arXiv.org arXiv:2512.03438v1 Announce Type: new
Abstract: Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed based on the final answers. Richer rewards computed from the reasoning tokens can improve learning significantly by providing more fine-grained guidance. However, it is challenging to compute more informative rewards in MMRL beyond those based on outcomes since different samples may require different scoring functions and teacher models may provide noisy reward signals too. In this paper, we introduce the Argos (Agentic Reward for Grounded & Objective Scoring), a principled reward agent to train multimodal reasoning models for agentic tasks. For each sample, Argos selects from a pool of teacher-model derived and rule-based scoring functions to simultaneously evaluate: (i) final response accuracy, (ii) spatiotemporal localization of referred entities and actions, and (iii) the quality of the reasoning process. We find that by leveraging our agentic verifier across both SFT data curation and RL training, our model achieves state-of-the-art results across multiple agentic tasks such as spatial reasoning, visual hallucination as well as robotics and embodied AI benchmarks. Critically, we demonstrate that just relying on SFT post-training on highly curated reasoning data is insufficient, as agents invariably collapse to ungrounded solutions during RL without our online verification. We also show that our agentic verifier can help to reduce reward-hacking in MMRL. Finally, we also provide a theoretical justification for the effectiveness of Argos through the concept of pareto-optimality.
arXiv:2512.03438v1 Announce Type: new
Abstract: Agentic reasoning models trained with multimodal reinforcement learning (MMRL) have become increasingly capable, yet they are almost universally optimized using sparse, outcome-based rewards computed based on the final answers. Richer rewards computed from the reasoning tokens can improve learning significantly by providing more fine-grained guidance. However, it is challenging to compute more informative rewards in MMRL beyond those based on outcomes since different samples may require different scoring functions and teacher models may provide noisy reward signals too. In this paper, we introduce the Argos (Agentic Reward for Grounded & Objective Scoring), a principled reward agent to train multimodal reasoning models for agentic tasks. For each sample, Argos selects from a pool of teacher-model derived and rule-based scoring functions to simultaneously evaluate: (i) final response accuracy, (ii) spatiotemporal localization of referred entities and actions, and (iii) the quality of the reasoning process. We find that by leveraging our agentic verifier across both SFT data curation and RL training, our model achieves state-of-the-art results across multiple agentic tasks such as spatial reasoning, visual hallucination as well as robotics and embodied AI benchmarks. Critically, we demonstrate that just relying on SFT post-training on highly curated reasoning data is insufficient, as agents invariably collapse to ungrounded solutions during RL without our online verification. We also show that our agentic verifier can help to reduce reward-hacking in MMRL. Finally, we also provide a theoretical justification for the effectiveness of Argos through the concept of pareto-optimality. Read More
PARC: An Autonomous Self-Reflective Coding Agent for Robust Execution of Long-Horizon Taskscs.AI updates on arXiv.org arXiv:2512.03549v1 Announce Type: new
Abstract: We introduce PARC, a coding agent for the autonomous and robust execution of long-horizon computational tasks. PARC is built on a hierarchical multi-agent architecture incorporating task planning, execution, and a mechanism that evaluates its own actions and their outcomes from an independent context and provides feedback, namely self-assessment and self-feedback. This design enables PARC to detect and correct high-level strategic errors and sustain progress without human intervention. We evaluate PARC across computational science and data science tasks. In materials science, it autonomously reproduces key results from studies on lithium-ion conduction and alloy segregation. In particular, it coordinates dozens of parallel simulation tasks, each requiring roughly 43 hours of computation, managing orchestration, monitoring, and error correction end-to-end. In Kaggle-based experiments, starting from minimal natural-language instructions, PARC conducts data analysis and implements search strategies, producing solutions competitive with human-engineered baselines. These results highlight the potential of integrating a hierarchical multi-agent system with self-assessment and self-feedback to enable AI systems capable of independent, large-scale scientific and analytical work.
arXiv:2512.03549v1 Announce Type: new
Abstract: We introduce PARC, a coding agent for the autonomous and robust execution of long-horizon computational tasks. PARC is built on a hierarchical multi-agent architecture incorporating task planning, execution, and a mechanism that evaluates its own actions and their outcomes from an independent context and provides feedback, namely self-assessment and self-feedback. This design enables PARC to detect and correct high-level strategic errors and sustain progress without human intervention. We evaluate PARC across computational science and data science tasks. In materials science, it autonomously reproduces key results from studies on lithium-ion conduction and alloy segregation. In particular, it coordinates dozens of parallel simulation tasks, each requiring roughly 43 hours of computation, managing orchestration, monitoring, and error correction end-to-end. In Kaggle-based experiments, starting from minimal natural-language instructions, PARC conducts data analysis and implements search strategies, producing solutions competitive with human-engineered baselines. These results highlight the potential of integrating a hierarchical multi-agent system with self-assessment and self-feedback to enable AI systems capable of independent, large-scale scientific and analytical work. Read More
AugMapNet: Improving Spatial Latent Structure via BEV Grid Augmentation for Enhanced Vectorized Online HD Map Constructioncs.AI updates on arXiv.org arXiv:2503.13430v2 Announce Type: replace-cross
Abstract: Autonomous driving requires understanding infrastructure elements, such as lanes and crosswalks. To navigate safely, this understanding must be derived from sensor data in real-time and needs to be represented in vectorized form. Learned Bird’s-Eye View (BEV) encoders are commonly used to combine a set of camera images from multiple views into one joint latent BEV grid. Traditionally, from this latent space, an intermediate raster map is predicted, providing dense spatial supervision but requiring post-processing into the desired vectorized form. More recent models directly derive infrastructure elements as polylines using vectorized map decoders, providing instance-level information. Our approach, Augmentation Map Network (AugMapNet), proposes latent BEV feature grid augmentation, a novel technique that significantly enhances the latent BEV representation. AugMapNet combines vector decoding and dense spatial supervision more effectively than existing architectures while remaining easy to integrate compared to other hybrid approaches. It additionally benefits from extra processing on its latent BEV features. Experiments on nuScenes and Argoverse2 datasets demonstrate significant improvements on vectorized map prediction of up to 13.3% over the StreamMapNet baseline on 60 m range and greater improvements on larger ranges. We confirm transferability by applying our method to another baseline, SQD-MapNet, and find similar improvements. A detailed analysis of the latent BEV grid confirms a more structured latent space of AugMapNet and shows the value of our novel concept beyond pure performance improvement. The code can be found at https://github.com/tmonnin/augmapnet
arXiv:2503.13430v2 Announce Type: replace-cross
Abstract: Autonomous driving requires understanding infrastructure elements, such as lanes and crosswalks. To navigate safely, this understanding must be derived from sensor data in real-time and needs to be represented in vectorized form. Learned Bird’s-Eye View (BEV) encoders are commonly used to combine a set of camera images from multiple views into one joint latent BEV grid. Traditionally, from this latent space, an intermediate raster map is predicted, providing dense spatial supervision but requiring post-processing into the desired vectorized form. More recent models directly derive infrastructure elements as polylines using vectorized map decoders, providing instance-level information. Our approach, Augmentation Map Network (AugMapNet), proposes latent BEV feature grid augmentation, a novel technique that significantly enhances the latent BEV representation. AugMapNet combines vector decoding and dense spatial supervision more effectively than existing architectures while remaining easy to integrate compared to other hybrid approaches. It additionally benefits from extra processing on its latent BEV features. Experiments on nuScenes and Argoverse2 datasets demonstrate significant improvements on vectorized map prediction of up to 13.3% over the StreamMapNet baseline on 60 m range and greater improvements on larger ranges. We confirm transferability by applying our method to another baseline, SQD-MapNet, and find similar improvements. A detailed analysis of the latent BEV grid confirms a more structured latent space of AugMapNet and shows the value of our novel concept beyond pure performance improvement. The code can be found at https://github.com/tmonnin/augmapnet Read More
Robust Tabular Foundation Modelscs.AI updates on arXiv.org arXiv:2512.03307v1 Announce Type: cross
Abstract: The development of tabular foundation models (TFMs) has accelerated in recent years, showing strong potential to outperform traditional ML methods for structured data. A key finding is that TFMs can be pretrained entirely on synthetic datasets, opening opportunities to design data generators that encourage desirable model properties. Prior work has mainly focused on crafting high-quality priors over generators to improve overall pretraining performance. Our insight is that parameterizing the generator distribution enables an adversarial robustness perspective: during training, we can adapt the generator to emphasize datasets that are particularly challenging for the model. We formalize this by introducing an optimality gap measure, given by the difference between TFM performance and the best achievable performance as estimated by strong baselines such as XGBoost, CatBoost, and Random Forests. Building on this idea, we propose Robust Tabular Foundation Models (RTFM), a model-agnostic adversarial training framework. Applied to the TabPFN V2 classifier, RTFM improves benchmark performance, with up to a 6% increase in mean normalized AUC over the original TabPFN and other baseline algorithms, while requiring less than 100k additional synthetic datasets. These results highlight a promising new direction for targeted adversarial training and fine-tuning of TFMs using synthetic data alone.
arXiv:2512.03307v1 Announce Type: cross
Abstract: The development of tabular foundation models (TFMs) has accelerated in recent years, showing strong potential to outperform traditional ML methods for structured data. A key finding is that TFMs can be pretrained entirely on synthetic datasets, opening opportunities to design data generators that encourage desirable model properties. Prior work has mainly focused on crafting high-quality priors over generators to improve overall pretraining performance. Our insight is that parameterizing the generator distribution enables an adversarial robustness perspective: during training, we can adapt the generator to emphasize datasets that are particularly challenging for the model. We formalize this by introducing an optimality gap measure, given by the difference between TFM performance and the best achievable performance as estimated by strong baselines such as XGBoost, CatBoost, and Random Forests. Building on this idea, we propose Robust Tabular Foundation Models (RTFM), a model-agnostic adversarial training framework. Applied to the TabPFN V2 classifier, RTFM improves benchmark performance, with up to a 6% increase in mean normalized AUC over the original TabPFN and other baseline algorithms, while requiring less than 100k additional synthetic datasets. These results highlight a promising new direction for targeted adversarial training and fine-tuning of TFMs using synthetic data alone. Read More
Exploring Syntropic Frameworks in AI Alignment: A Philosophical Investigationcs.AI updates on arXiv.org arXiv:2512.03048v1 Announce Type: new
Abstract: I argue that AI alignment should be reconceived as architecting syntropic, reasons-responsive agents through process-based, multi-agent, developmental mechanisms rather than encoding fixed human value content. The paper makes three philosophical contributions. First, I articulate the “specification trap” argument demonstrating why content-based value specification appears structurally unstable due to the conjunction of the is-ought gap, value pluralism, and the extended frame problem. Second, I propose syntropy — the recursive reduction of mutual uncertainty between agents through state alignment — as an information-theoretic framework for understanding multi-agent alignment dynamics. Third, I establish a functional distinction between genuine and simulated moral capacity grounded in compatibilist theories of guidance control, coupled with an embodied experimental paradigm and verification regime providing operational criteria independent of phenomenological claims. This paper represents the philosophical component of a broader research program whose empirical validation is being developed in a separate project currently in preparation. While the framework generates specific, falsifiable predictions about value emergence and moral agency in artificial systems, empirical validation remains pending.
arXiv:2512.03048v1 Announce Type: new
Abstract: I argue that AI alignment should be reconceived as architecting syntropic, reasons-responsive agents through process-based, multi-agent, developmental mechanisms rather than encoding fixed human value content. The paper makes three philosophical contributions. First, I articulate the “specification trap” argument demonstrating why content-based value specification appears structurally unstable due to the conjunction of the is-ought gap, value pluralism, and the extended frame problem. Second, I propose syntropy — the recursive reduction of mutual uncertainty between agents through state alignment — as an information-theoretic framework for understanding multi-agent alignment dynamics. Third, I establish a functional distinction between genuine and simulated moral capacity grounded in compatibilist theories of guidance control, coupled with an embodied experimental paradigm and verification regime providing operational criteria independent of phenomenological claims. This paper represents the philosophical component of a broader research program whose empirical validation is being developed in a separate project currently in preparation. While the framework generates specific, falsifiable predictions about value emergence and moral agency in artificial systems, empirical validation remains pending. Read More
A Learning-based Control Methodology for Transitioning VTOL UAVscs.AI updates on arXiv.org arXiv:2512.03548v1 Announce Type: cross
Abstract: Transition control poses a critical challenge in Vertical Take-Off and Landing Unmanned Aerial Vehicle (VTOL UAV) development due to the tilting rotor mechanism, which shifts the center of gravity and thrust direction during transitions. Current control methods’ decoupled control of altitude and position leads to significant vibration, and limits interaction consideration and adaptability. In this study, we propose a novel coupled transition control methodology based on reinforcement learning (RL) driven controller. Besides, contrasting to the conventional phase-transition approach, the ST3M method demonstrates a new perspective by treating cruise mode as a special case of hover. We validate the feasibility of applying our method in simulation and real-world environments, demonstrating efficient controller development and migration while accurately controlling UAV position and attitude, exhibiting outstanding trajectory tracking and reduced vibrations during the transition process.
arXiv:2512.03548v1 Announce Type: cross
Abstract: Transition control poses a critical challenge in Vertical Take-Off and Landing Unmanned Aerial Vehicle (VTOL UAV) development due to the tilting rotor mechanism, which shifts the center of gravity and thrust direction during transitions. Current control methods’ decoupled control of altitude and position leads to significant vibration, and limits interaction consideration and adaptability. In this study, we propose a novel coupled transition control methodology based on reinforcement learning (RL) driven controller. Besides, contrasting to the conventional phase-transition approach, the ST3M method demonstrates a new perspective by treating cruise mode as a special case of hover. We validate the feasibility of applying our method in simulation and real-world environments, demonstrating efficient controller development and migration while accurately controlling UAV position and attitude, exhibiting outstanding trajectory tracking and reduced vibrations during the transition process. Read More
The promising potential of vision language models for the generation of textual weather forecastscs.AI updates on arXiv.org arXiv:2512.03623v1 Announce Type: cross
Abstract: Despite the promising capability of multimodal foundation models, their application to the generation of meteorological products and services remains nascent. To accelerate aspiration and adoption, we explore the novel use of a vision language model for writing the iconic Shipping Forecast text directly from video-encoded gridded weather data. These early results demonstrate promising scalable technological opportunities for enhancing production efficiency and service innovation within the weather enterprise and beyond.
arXiv:2512.03623v1 Announce Type: cross
Abstract: Despite the promising capability of multimodal foundation models, their application to the generation of meteorological products and services remains nascent. To accelerate aspiration and adoption, we explore the novel use of a vision language model for writing the iconic Shipping Forecast text directly from video-encoded gridded weather data. These early results demonstrate promising scalable technological opportunities for enhancing production efficiency and service innovation within the weather enterprise and beyond. Read More
Introducing OpenAI for AustraliaOpenAI News OpenAI is launching OpenAI for Australia to build sovereign AI infrastructure, upskill more than 1.5 million workers, and accelerate innovation across the country’s growing AI ecosystem.
OpenAI is launching OpenAI for Australia to build sovereign AI infrastructure, upskill more than 1.5 million workers, and accelerate innovation across the country’s growing AI ecosystem. Read More
5 Critical Feature Engineering Mistakes That Kill Machine Learning ProjectsKDnuggets Check out this comprehensive guide to building production-ready features that actually work.
Check out this comprehensive guide to building production-ready features that actually work. Read More
AWS re:Invent 2025: Frontier AI agents replace chatbotsAI News According to AWS at this week’s re:Invent 2025, the chatbot hype cycle is effectively dead, with frontier AI agents taking their place. That is the blunt message radiating from Las Vegas this week. The industry’s obsession with chat interfaces has been replaced by a far more demanding mandate: “frontier agents” that don’t just talk, but
The post AWS re:Invent 2025: Frontier AI agents replace chatbots appeared first on AI News.
According to AWS at this week’s re:Invent 2025, the chatbot hype cycle is effectively dead, with frontier AI agents taking their place. That is the blunt message radiating from Las Vegas this week. The industry’s obsession with chat interfaces has been replaced by a far more demanding mandate: “frontier agents” that don’t just talk, but
The post AWS re:Invent 2025: Frontier AI agents replace chatbots appeared first on AI News. Read More