Category: News

AgentNoiseBench: Benchmarking Robustness of Tool-Using LLM Agents Under Noisy Conditioncs.AI updates on arXiv.org arXiv:2602.11348v1 Announce Type: new
Abstract: Recent advances in large language models have enabled LLM-based agents to achieve strong performance on a variety of benchmarks. However, their performance in real-world deployments often that observed on benchmark settings, especially in complex and imperfect environments. This discrepancy largely arises because prevailing training and evaluation paradigms are typically built on idealized assumptions, overlooking the inherent stochasticity and noise present in real-world interactions. To bridge this gap, we introduce AgentNoiseBench, a framework for systematically evaluating the robustness of agentic models under noisy environments. We first conduct an in-depth analysis of biases and uncertainties in real-world scenarios and categorize environmental noise into two primary types: user-noise and tool-noise. Building on this analysis, we develop an automated pipeline that injects controllable noise into existing agent-centric benchmarks while preserving task solvability. Leveraging this pipeline, we perform extensive evaluations across a wide range of models with diverse architectures and parameter scales. Our results reveal consistent performance variations under different noise conditions, highlighting the sensitivity of current agentic models to realistic environmental perturbations.

 arXiv:2602.11348v1 Announce Type: new
Abstract: Recent advances in large language models have enabled LLM-based agents to achieve strong performance on a variety of benchmarks. However, their performance in real-world deployments often that observed on benchmark settings, especially in complex and imperfect environments. This discrepancy largely arises because prevailing training and evaluation paradigms are typically built on idealized assumptions, overlooking the inherent stochasticity and noise present in real-world interactions. To bridge this gap, we introduce AgentNoiseBench, a framework for systematically evaluating the robustness of agentic models under noisy environments. We first conduct an in-depth analysis of biases and uncertainties in real-world scenarios and categorize environmental noise into two primary types: user-noise and tool-noise. Building on this analysis, we develop an automated pipeline that injects controllable noise into existing agent-centric benchmarks while preserving task solvability. Leveraging this pipeline, we perform extensive evaluations across a wide range of models with diverse architectures and parameter scales. Our results reveal consistent performance variations under different noise conditions, highlighting the sensitivity of current agentic models to realistic environmental perturbations. Read More  

Manifold-Aware Temporal Domain Generalization for Large Language Modelscs.AI updates on arXiv.org arXiv:2602.11965v1 Announce Type: cross
Abstract: Temporal distribution shifts are pervasive in real-world deployments of Large Language Models (LLMs), where data evolves continuously over time. While Temporal Domain Generalization (TDG) seeks to model such structured evolution, existing approaches characterize model adaptation in the full parameter space. This formulation becomes computationally infeasible for modern LLMs. This paper introduces a geometric reformulation of TDG under parameter-efficient fine-tuning. We establish that the low-dimensional temporal structure underlying model evolution can be preserved under parameter-efficient reparameterization, enabling temporal modeling without operating in the ambient parameter space. Building on this principle, we propose Manifold-aware Temporal LoRA (MaT-LoRA), which constrains temporal updates to a shared low-dimensional manifold within a low-rank adaptation subspace, and models its evolution through a structured temporal core. This reparameterization dramatically reduces temporal modeling complexity while retaining expressive power. Extensive experiments on synthetic and real-world datasets, including scientific documents, news publishers, and review ratings, demonstrate that MaT-LoRA achieves superior temporal generalization performance with practical scalability for LLMs.

 arXiv:2602.11965v1 Announce Type: cross
Abstract: Temporal distribution shifts are pervasive in real-world deployments of Large Language Models (LLMs), where data evolves continuously over time. While Temporal Domain Generalization (TDG) seeks to model such structured evolution, existing approaches characterize model adaptation in the full parameter space. This formulation becomes computationally infeasible for modern LLMs. This paper introduces a geometric reformulation of TDG under parameter-efficient fine-tuning. We establish that the low-dimensional temporal structure underlying model evolution can be preserved under parameter-efficient reparameterization, enabling temporal modeling without operating in the ambient parameter space. Building on this principle, we propose Manifold-aware Temporal LoRA (MaT-LoRA), which constrains temporal updates to a shared low-dimensional manifold within a low-rank adaptation subspace, and models its evolution through a structured temporal core. This reparameterization dramatically reduces temporal modeling complexity while retaining expressive power. Extensive experiments on synthetic and real-world datasets, including scientific documents, news publishers, and review ratings, demonstrate that MaT-LoRA achieves superior temporal generalization performance with practical scalability for LLMs. Read More  

Improving Neural Retrieval with Attribution-Guided Query Rewritingcs.AI updates on arXiv.org arXiv:2602.11841v1 Announce Type: cross
Abstract: Neural retrievers are effective but brittle: underspecified or ambiguous queries can misdirect ranking even when relevant documents exist. Existing approaches address this brittleness only partially: LLMs rewrite queries without retriever feedback, and explainability methods identify misleading tokens but are used for post-hoc analysis. We close this loop and propose an attribution-guided query rewriting method that uses token-level explanations to guide query rewriting. For each query, we compute gradient-based token attributions from the retriever and then use these scores as soft guidance in a structured prompt to an LLM that clarifies weak or misleading query components while preserving intent. Evaluated on BEIR collections, the resulting rewrites consistently improve retrieval effectiveness over strong baselines, with larger gains for implicit or ambiguous information needs.

 arXiv:2602.11841v1 Announce Type: cross
Abstract: Neural retrievers are effective but brittle: underspecified or ambiguous queries can misdirect ranking even when relevant documents exist. Existing approaches address this brittleness only partially: LLMs rewrite queries without retriever feedback, and explainability methods identify misleading tokens but are used for post-hoc analysis. We close this loop and propose an attribution-guided query rewriting method that uses token-level explanations to guide query rewriting. For each query, we compute gradient-based token attributions from the retriever and then use these scores as soft guidance in a structured prompt to an LLM that clarifies weak or misleading query components while preserving intent. Evaluated on BEIR collections, the resulting rewrites consistently improve retrieval effectiveness over strong baselines, with larger gains for implicit or ambiguous information needs. Read More  

Fin-RATE: A Real-world Financial Analytics and Tracking Evaluation Benchmark for LLMs on SEC Filingscs.AI updates on arXiv.org arXiv:2602.07294v2 Announce Type: replace-cross
Abstract: With the increasing deployment of Large Language Models (LLMs) in the finance domain, LLMs are increasingly expected to parse complex regulatory disclosures. However, existing benchmarks often focus on isolated details, failing to reflect the complexity of professional analysis that requires synthesizing information across multiple documents, reporting periods, and corporate entities. Furthermore, these benchmarks do not disentangle whether errors arise from retrieval failures, generation inaccuracies, domain-specific reasoning mistakes, or misinterpretation of the query or context, making it difficult to precisely diagnose performance bottlenecks. To bridge these gaps, we introduce Fin-RATE, a benchmark built on U.S. Securities and Exchange Commission (SEC) filings and mirroring financial analyst workflows through three pathways: detail-oriented reasoning within individual disclosures, cross-entity comparison under shared topics, and longitudinal tracking of the same firm across reporting periods. We benchmark 17 leading LLMs, spanning open-source, closed-source, and finance-specialized models, under both ground-truth context and retrieval-augmented settings. Results show substantial performance degradation, with accuracy dropping by 18.60% and 14.35% as tasks shift from single-document reasoning to longitudinal and cross-entity analysis. This degradation is driven by increased comparison hallucinations, temporal and entity mismatches, and is further reflected in declines in reasoning quality and factual consistency–limitations that existing benchmarks have yet to formally categorize or quantify.

 arXiv:2602.07294v2 Announce Type: replace-cross
Abstract: With the increasing deployment of Large Language Models (LLMs) in the finance domain, LLMs are increasingly expected to parse complex regulatory disclosures. However, existing benchmarks often focus on isolated details, failing to reflect the complexity of professional analysis that requires synthesizing information across multiple documents, reporting periods, and corporate entities. Furthermore, these benchmarks do not disentangle whether errors arise from retrieval failures, generation inaccuracies, domain-specific reasoning mistakes, or misinterpretation of the query or context, making it difficult to precisely diagnose performance bottlenecks. To bridge these gaps, we introduce Fin-RATE, a benchmark built on U.S. Securities and Exchange Commission (SEC) filings and mirroring financial analyst workflows through three pathways: detail-oriented reasoning within individual disclosures, cross-entity comparison under shared topics, and longitudinal tracking of the same firm across reporting periods. We benchmark 17 leading LLMs, spanning open-source, closed-source, and finance-specialized models, under both ground-truth context and retrieval-augmented settings. Results show substantial performance degradation, with accuracy dropping by 18.60% and 14.35% as tasks shift from single-document reasoning to longitudinal and cross-entity analysis. This degradation is driven by increased comparison hallucinations, temporal and entity mismatches, and is further reflected in declines in reasoning quality and factual consistency–limitations that existing benchmarks have yet to formally categorize or quantify. Read More  

Google DeepMind Introduces Aletheia: The AI Agent Moving from Math Competitions to Fully Autonomous Professional Research DiscoveriesMarkTechPost Google DeepMind team has introduced Aletheia, a specialized AI agent designed to bridge the gap between competition-level math and professional research. While models achieved gold-medal standards at the 2025 International Mathematical Olympiad (IMO), research requires navigating vast literature and constructing long-horizon proofs. Aletheia solves this by iteratively generating, verifying, and revising solutions in natural language.
The post Google DeepMind Introduces Aletheia: The AI Agent Moving from Math Competitions to Fully Autonomous Professional Research Discoveries appeared first on MarkTechPost.

 Google DeepMind team has introduced Aletheia, a specialized AI agent designed to bridge the gap between competition-level math and professional research. While models achieved gold-medal standards at the 2025 International Mathematical Olympiad (IMO), research requires navigating vast literature and constructing long-horizon proofs. Aletheia solves this by iteratively generating, verifying, and revising solutions in natural language.
The post Google DeepMind Introduces Aletheia: The AI Agent Moving from Math Competitions to Fully Autonomous Professional Research Discoveries appeared first on MarkTechPost. Read More  

DeepRead: Document Structure-Aware Reasoning to Enhance Agentic Searchcs.AI updates on arXiv.org arXiv:2602.05014v3 Announce Type: replace
Abstract: With the rapid advancement of tool-use capabilities in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) is shifting from static, one-shot retrieval toward autonomous, multi-turn evidence acquisition. However, existing agentic search frameworks typically treat long documents as flat collections of unstructured chunks, disregarding the native hierarchical organization and sequential logic essential for human comprehension. To bridge this gap, we introduce textbf{DeepRead}, a structure-aware document reasoning agent designed to operationalize document-native structural priors into actionable reasoning capabilities. Leveraging the structural fidelity of modern OCR, DeepRead constructs a paragraph-level, coordinate-based navigation system and equips the LLM with two synergistic tools: textsf{Retrieve} for scanning-aware localization, and textsf{ReadSection} for contiguous, order-preserving reading within specific hierarchical scopes. This design elicits a human-like “locate-then-read” reasoning paradigm, effectively mitigating the context fragmentation inherent in traditional retrieval methods. Extensive evaluations across four benchmarks spanning diverse document types demonstrate that DeepRead outperforms Search-o1-style agentic search baselines by an average of 10.3%. Fine-grained behavioral analysis further confirms that DeepRead autonomously adopts human-aligned reading strategies, validating the critical role of structural awareness in achieving precise document reasoning. Our code is available at https://github.com/Zhanli-Li/DeepRead.

 arXiv:2602.05014v3 Announce Type: replace
Abstract: With the rapid advancement of tool-use capabilities in Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) is shifting from static, one-shot retrieval toward autonomous, multi-turn evidence acquisition. However, existing agentic search frameworks typically treat long documents as flat collections of unstructured chunks, disregarding the native hierarchical organization and sequential logic essential for human comprehension. To bridge this gap, we introduce textbf{DeepRead}, a structure-aware document reasoning agent designed to operationalize document-native structural priors into actionable reasoning capabilities. Leveraging the structural fidelity of modern OCR, DeepRead constructs a paragraph-level, coordinate-based navigation system and equips the LLM with two synergistic tools: textsf{Retrieve} for scanning-aware localization, and textsf{ReadSection} for contiguous, order-preserving reading within specific hierarchical scopes. This design elicits a human-like “locate-then-read” reasoning paradigm, effectively mitigating the context fragmentation inherent in traditional retrieval methods. Extensive evaluations across four benchmarks spanning diverse document types demonstrate that DeepRead outperforms Search-o1-style agentic search baselines by an average of 10.3%. Fine-grained behavioral analysis further confirms that DeepRead autonomously adopts human-aligned reading strategies, validating the critical role of structural awareness in achieving precise document reasoning. Our code is available at https://github.com/Zhanli-Li/DeepRead. Read More  

AI in Multiple GPUs: Point-to-Point and Collective OperationsTowards Data Science Learn PyTorch distributed operations for multi GPU AI workloads
The post AI in Multiple GPUs: Point-to-Point and Collective Operations appeared first on Towards Data Science.

 Learn PyTorch distributed operations for multi GPU AI workloads
The post AI in Multiple GPUs: Point-to-Point and Collective Operations appeared first on Towards Data Science. Read More  

Agentic AI drives finance ROI in accounts payable automationAI News Finance leaders are driving ROI using agentic AI for accounts payable automation, turning manual tasks into autonomous workflows. While general AI projects saw return on investment rise to 67 percent last year, autonomous agents delivered an average ROI of 80 percent by handling complex processes without human intervention. This performance gap demands a change in
The post Agentic AI drives finance ROI in accounts payable automation appeared first on AI News.

 Finance leaders are driving ROI using agentic AI for accounts payable automation, turning manual tasks into autonomous workflows. While general AI projects saw return on investment rise to 67 percent last year, autonomous agents delivered an average ROI of 80 percent by handling complex processes without human intervention. This performance gap demands a change in
The post Agentic AI drives finance ROI in accounts payable automation appeared first on AI News. Read More  

Newsweek CEO Dev Pragad warns publishers: adapt as AI becomes news gatewayAI News Author: Dev Pragad, CEO, Newsweek As artificial intelligence platforms increasingly mediate how people encounter news, media leaders are confronting an important change in the relationship between journalism and the public. AI-driven search and conversational interfaces now influence how audiences discover and trust information, often before visiting a publisher’s website. According to Dev Pragad, the implications
The post Newsweek CEO Dev Pragad warns publishers: adapt as AI becomes news gateway appeared first on AI News.

 Author: Dev Pragad, CEO, Newsweek As artificial intelligence platforms increasingly mediate how people encounter news, media leaders are confronting an important change in the relationship between journalism and the public. AI-driven search and conversational interfaces now influence how audiences discover and trust information, often before visiting a publisher’s website. According to Dev Pragad, the implications
The post Newsweek CEO Dev Pragad warns publishers: adapt as AI becomes news gateway appeared first on AI News. Read More