Category: News

POLARIS: Typed Planning and Governed Execution for Agentic AI in Back-Office Automationcs.AI updates on arXiv.org arXiv:2601.11816v1 Announce Type: new
Abstract: Enterprise back office workflows require agentic systems that are auditable, policy-aligned, and operationally predictable, capabilities that generic multi-agent setups often fail to deliver. We present POLARIS (Policy-Aware LLM Agentic Reasoning for Integrated Systems), a governed orchestration framework that treats automation as typed plan synthesis and validated execution over LLM agents. A planner proposes structurally diverse, type checked directed acyclic graphs (DAGs), a rubric guided reasoning module selects a single compliant plan, and execution is guarded by validator gated checks, a bounded repair loop, and compiled policy guardrails that block or route side effects before they occur. Applied to document centric finance tasks, POLARIS produces decision grade artifacts and full execution traces while reducing human intervention. Empirically, POLARIS achieves a micro F1 of 0.81 on the SROIE dataset and, on a controlled synthetic suite, achieves 0.95 to 1.00 precision for anomaly routing with preserved audit trails. These evaluations constitute an initial benchmark for governed Agentic AI. POLARIS provides a methodological and benchmark reference for policy-aligned Agentic AI. Keywords Agentic AI, Enterprise Automation, Back-Office Tasks, Benchmarks, Governance, Typed Planning, Evaluation

 arXiv:2601.11816v1 Announce Type: new
Abstract: Enterprise back office workflows require agentic systems that are auditable, policy-aligned, and operationally predictable, capabilities that generic multi-agent setups often fail to deliver. We present POLARIS (Policy-Aware LLM Agentic Reasoning for Integrated Systems), a governed orchestration framework that treats automation as typed plan synthesis and validated execution over LLM agents. A planner proposes structurally diverse, type checked directed acyclic graphs (DAGs), a rubric guided reasoning module selects a single compliant plan, and execution is guarded by validator gated checks, a bounded repair loop, and compiled policy guardrails that block or route side effects before they occur. Applied to document centric finance tasks, POLARIS produces decision grade artifacts and full execution traces while reducing human intervention. Empirically, POLARIS achieves a micro F1 of 0.81 on the SROIE dataset and, on a controlled synthetic suite, achieves 0.95 to 1.00 precision for anomaly routing with preserved audit trails. These evaluations constitute an initial benchmark for governed Agentic AI. POLARIS provides a methodological and benchmark reference for policy-aligned Agentic AI. Keywords Agentic AI, Enterprise Automation, Back-Office Tasks, Benchmarks, Governance, Typed Planning, Evaluation Read More  

Towards a Unified View of Large Language Model Post-Trainingcs.AI updates on arXiv.org arXiv:2509.04419v2 Announce Type: replace-cross
Abstract: Two major sources of training data exist for post-training modern language models: online (model-generated rollouts) data, and offline (human or other-model demonstrations) data. These two types of data are typically used by approaches like Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT), respectively. In this paper, we show that these approaches are not in contradiction, but are instances of a single optimization process. We derive a Unified Policy Gradient Estimator, and present the calculations of a wide spectrum of post-training approaches as the gradient of a common objective under different data distribution assumptions and various bias-variance tradeoffs. The gradient estimator is constructed with four interchangeable parts: stabilization mask, reference policy denominator, advantage estimate, and likelihood gradient. Motivated by our theoretical findings, we propose Hybrid Post-Training (HPT), an algorithm that dynamically selects different training signals. HPT is designed to yield both effective exploitation of demonstration and stable exploration without sacrificing learned reasoning patterns. We provide extensive experiments and ablation studies to verify the effectiveness of our unified theoretical framework and HPT. Across six mathematical reasoning benchmarks and two out-of-distribution suites, HPT consistently surpasses strong baselines across models of varying scales and families.

 arXiv:2509.04419v2 Announce Type: replace-cross
Abstract: Two major sources of training data exist for post-training modern language models: online (model-generated rollouts) data, and offline (human or other-model demonstrations) data. These two types of data are typically used by approaches like Reinforcement Learning (RL) and Supervised Fine-Tuning (SFT), respectively. In this paper, we show that these approaches are not in contradiction, but are instances of a single optimization process. We derive a Unified Policy Gradient Estimator, and present the calculations of a wide spectrum of post-training approaches as the gradient of a common objective under different data distribution assumptions and various bias-variance tradeoffs. The gradient estimator is constructed with four interchangeable parts: stabilization mask, reference policy denominator, advantage estimate, and likelihood gradient. Motivated by our theoretical findings, we propose Hybrid Post-Training (HPT), an algorithm that dynamically selects different training signals. HPT is designed to yield both effective exploitation of demonstration and stable exploration without sacrificing learned reasoning patterns. We provide extensive experiments and ablation studies to verify the effectiveness of our unified theoretical framework and HPT. Across six mathematical reasoning benchmarks and two out-of-distribution suites, HPT consistently surpasses strong baselines across models of varying scales and families. Read More  

TractRLFusion: A GPT-Based Multi-Critic Policy Fusion Framework for Fiber Tractographycs.AI updates on arXiv.org arXiv:2601.13897v1 Announce Type: cross
Abstract: Tractography plays a pivotal role in the non-invasive reconstruction of white matter fiber pathways, providing vital information on brain connectivity and supporting precise neurosurgical planning. Although traditional methods relied mainly on classical deterministic and probabilistic approaches, recent progress has benefited from supervised deep learning (DL) and deep reinforcement learning (DRL) to improve tract reconstruction. A persistent challenge in tractography is accurately reconstructing white matter tracts while minimizing spurious connections. To address this, we propose TractRLFusion, a novel GPT-based policy fusion framework that integrates multiple RL policies through a data-driven fusion strategy. Our method employs a two-stage training data selection process for effective policy fusion, followed by a multi-critic fine-tuning phase to enhance robustness and generalization. Experiments on HCP, ISMRM, and TractoInferno datasets demonstrate that TractRLFusion outperforms individual RL policies as well as state-of-the-art classical and DRL methods in accuracy and anatomical reliability.

 arXiv:2601.13897v1 Announce Type: cross
Abstract: Tractography plays a pivotal role in the non-invasive reconstruction of white matter fiber pathways, providing vital information on brain connectivity and supporting precise neurosurgical planning. Although traditional methods relied mainly on classical deterministic and probabilistic approaches, recent progress has benefited from supervised deep learning (DL) and deep reinforcement learning (DRL) to improve tract reconstruction. A persistent challenge in tractography is accurately reconstructing white matter tracts while minimizing spurious connections. To address this, we propose TractRLFusion, a novel GPT-based policy fusion framework that integrates multiple RL policies through a data-driven fusion strategy. Our method employs a two-stage training data selection process for effective policy fusion, followed by a multi-critic fine-tuning phase to enhance robustness and generalization. Experiments on HCP, ISMRM, and TractoInferno datasets demonstrate that TractRLFusion outperforms individual RL policies as well as state-of-the-art classical and DRL methods in accuracy and anatomical reliability. Read More  

When Hallucination Costs Millions: Benchmarking AI Agents in High-Stakes Adversarial Financial Marketscs.AI updates on arXiv.org arXiv:2510.00332v2 Announce Type: replace
Abstract: We present CAIA, a benchmark exposing a critical blind spot in AI evaluation: the inability of state-of-the-art models to operate in adversarial, high-stakes environments where misinformation is weaponized and errors are irreversible. While existing benchmarks measure task completion in controlled settings, real-world deployment demands resilience against active deception. Using crypto markets as a testbed where $30 billion was lost to exploits in 2024, we evaluate 17 models on 178 time-anchored tasks requiring agents to distinguish truth from manipulation, navigate fragmented information landscapes, and make irreversible financial decisions under adversarial pressure.
Our results reveal a fundamental capability gap: without tools, even frontier models achieve only 28% accuracy on tasks junior analysts routinely handle. Tool augmentation improves performance but plateaus at 67.4% versus 80% human baseline, despite unlimited access to professional resources. Most critically, we uncover a systematic tool selection catastrophe: models preferentially choose unreliable web search over authoritative data, falling for SEO-optimized misinformation and social media manipulation. This behavior persists even when correct answers are directly accessible through specialized tools, suggesting foundational limitations rather than knowledge gaps. We also find that Pass@k metrics mask dangerous trial-and-error behavior for autonomous deployment.
The implications extend beyond crypto to any domain with active adversaries, e.g. cybersecurity, content moderation, etc. We release CAIA with contamination controls and continuous updates, establishing adversarial robustness as a necessary condition for trustworthy AI autonomy. The benchmark reveals that current models, despite impressive reasoning scores, remain fundamentally unprepared for environments where intelligence must survive active opposition.

 arXiv:2510.00332v2 Announce Type: replace
Abstract: We present CAIA, a benchmark exposing a critical blind spot in AI evaluation: the inability of state-of-the-art models to operate in adversarial, high-stakes environments where misinformation is weaponized and errors are irreversible. While existing benchmarks measure task completion in controlled settings, real-world deployment demands resilience against active deception. Using crypto markets as a testbed where $30 billion was lost to exploits in 2024, we evaluate 17 models on 178 time-anchored tasks requiring agents to distinguish truth from manipulation, navigate fragmented information landscapes, and make irreversible financial decisions under adversarial pressure.
Our results reveal a fundamental capability gap: without tools, even frontier models achieve only 28% accuracy on tasks junior analysts routinely handle. Tool augmentation improves performance but plateaus at 67.4% versus 80% human baseline, despite unlimited access to professional resources. Most critically, we uncover a systematic tool selection catastrophe: models preferentially choose unreliable web search over authoritative data, falling for SEO-optimized misinformation and social media manipulation. This behavior persists even when correct answers are directly accessible through specialized tools, suggesting foundational limitations rather than knowledge gaps. We also find that Pass@k metrics mask dangerous trial-and-error behavior for autonomous deployment.
The implications extend beyond crypto to any domain with active adversaries, e.g. cybersecurity, content moderation, etc. We release CAIA with contamination controls and continuous updates, establishing adversarial robustness as a necessary condition for trustworthy AI autonomy. The benchmark reveals that current models, despite impressive reasoning scores, remain fundamentally unprepared for environments where intelligence must survive active opposition. Read More  

The quiet work behind Citi’s 4,000-person internal AI rolloutAI News For many large companies, artificial intelligence still lives in side projects. Small teams test tools, run pilots, and present results that struggle to spread beyond a few departments. Citi has taken a different path, where instead of keeping AI limited to specialists, the bank has spent the past two years pushing the technology into daily
The post The quiet work behind Citi’s 4,000-person internal AI rollout appeared first on AI News.

 For many large companies, artificial intelligence still lives in side projects. Small teams test tools, run pilots, and present results that struggle to spread beyond a few departments. Citi has taken a different path, where instead of keeping AI limited to specialists, the bank has spent the past two years pushing the technology into daily
The post The quiet work behind Citi’s 4,000-person internal AI rollout appeared first on AI News. Read More  

From Prompts to Pavement: LMMs-based Agentic Behavior-Tree Generation Framework for Autonomous Vehiclescs.AI updates on arXiv.org arXiv:2601.12358v1 Announce Type: cross
Abstract: Autonomous vehicles (AVs) require adaptive behavior planners to navigate unpredictable, real-world environments safely. Traditional behavior trees (BTs) offer structured decision logic but are inherently static and demand labor-intensive manual tuning, limiting their applicability at SAE Level 5 autonomy. This paper presents an agentic framework that leverages large language models (LLMs) and multi-modal vision models (LVMs) to generate and adapt BTs on the fly. A specialized Descriptor agent applies chain-of-symbols prompting to assess scene criticality, a Planner agent constructs high-level sub-goals via in-context learning, and a Generator agent synthesizes executable BT sub-trees in XML format. Integrated into a CARLA+Nav2 simulation, our system triggers only upon baseline BT failure, demonstrating successful navigation around unexpected obstacles (e.g., street blockage) with no human intervention. Compared to a static BT baseline, this approach is a proof-of-concept that extends to diverse driving scenarios.

 arXiv:2601.12358v1 Announce Type: cross
Abstract: Autonomous vehicles (AVs) require adaptive behavior planners to navigate unpredictable, real-world environments safely. Traditional behavior trees (BTs) offer structured decision logic but are inherently static and demand labor-intensive manual tuning, limiting their applicability at SAE Level 5 autonomy. This paper presents an agentic framework that leverages large language models (LLMs) and multi-modal vision models (LVMs) to generate and adapt BTs on the fly. A specialized Descriptor agent applies chain-of-symbols prompting to assess scene criticality, a Planner agent constructs high-level sub-goals via in-context learning, and a Generator agent synthesizes executable BT sub-trees in XML format. Integrated into a CARLA+Nav2 simulation, our system triggers only upon baseline BT failure, demonstrating successful navigation around unexpected obstacles (e.g., street blockage) with no human intervention. Compared to a static BT baseline, this approach is a proof-of-concept that extends to diverse driving scenarios. Read More  

We Tuned 4 Classifiers on the Same Dataset: None Actually ImprovedKDnuggets We tuned four classifiers on student performance data with proper nested cross-validation and statistical testing. The result? Tuning changed nothing.

 We tuned four classifiers on student performance data with proper nested cross-validation and statistical testing. The result? Tuning changed nothing. Read More