AgentEvolver: Towards Efficient Self-Evolving Agent Systemcs.AI updates on arXiv.org arXiv:2511.10395v1 Announce Type: cross
Abstract: Autonomous agents powered by large language models (LLMs) have the potential to significantly enhance human productivity by reasoning, using tools, and executing complex tasks in diverse environments. However, current approaches to developing such agents remain costly and inefficient, as they typically require manually constructed task datasets and reinforcement learning (RL) pipelines with extensive random exploration. These limitations lead to prohibitively high data-construction costs, low exploration efficiency, and poor sample utilization. To address these challenges, we present AgentEvolver, a self-evolving agent system that leverages the semantic understanding and reasoning capabilities of LLMs to drive autonomous agent learning. AgentEvolver introduces three synergistic mechanisms: (i) self-questioning, which enables curiosity-driven task generation in novel environments, reducing dependence on handcrafted datasets; (ii) self-navigating, which improves exploration efficiency through experience reuse and hybrid policy guidance; and (iii) self-attributing, which enhances sample efficiency by assigning differentiated rewards to trajectory states and actions based on their contribution. By integrating these mechanisms into a unified framework, AgentEvolver enables scalable, cost-effective, and continual improvement of agent capabilities. Preliminary experiments indicate that AgentEvolver achieves more efficient exploration, better sample utilization, and faster adaptation compared to traditional RL-based baselines.
arXiv:2511.10395v1 Announce Type: cross
Abstract: Autonomous agents powered by large language models (LLMs) have the potential to significantly enhance human productivity by reasoning, using tools, and executing complex tasks in diverse environments. However, current approaches to developing such agents remain costly and inefficient, as they typically require manually constructed task datasets and reinforcement learning (RL) pipelines with extensive random exploration. These limitations lead to prohibitively high data-construction costs, low exploration efficiency, and poor sample utilization. To address these challenges, we present AgentEvolver, a self-evolving agent system that leverages the semantic understanding and reasoning capabilities of LLMs to drive autonomous agent learning. AgentEvolver introduces three synergistic mechanisms: (i) self-questioning, which enables curiosity-driven task generation in novel environments, reducing dependence on handcrafted datasets; (ii) self-navigating, which improves exploration efficiency through experience reuse and hybrid policy guidance; and (iii) self-attributing, which enhances sample efficiency by assigning differentiated rewards to trajectory states and actions based on their contribution. By integrating these mechanisms into a unified framework, AgentEvolver enables scalable, cost-effective, and continual improvement of agent capabilities. Preliminary experiments indicate that AgentEvolver achieves more efficient exploration, better sample utilization, and faster adaptation compared to traditional RL-based baselines. Read More
WOD-E2E: Waymo Open Dataset for End-to-End Driving in Challenging Long-tail Scenarioscs.AI updates on arXiv.org arXiv:2510.26125v3 Announce Type: replace-cross
Abstract: Vision-based end-to-end (E2E) driving has garnered significant interest in the research community due to its scalability and synergy with multimodal large language models (MLLMs). However, current E2E driving benchmarks primarily feature nominal scenarios, failing to adequately test the true potential of these systems. Furthermore, existing open-loop evaluation metrics often fall short in capturing the multi-modal nature of driving or effectively evaluating performance in long-tail scenarios. To address these gaps, we introduce the Waymo Open Dataset for End-to-End Driving (WOD-E2E). WOD-E2E contains 4,021 driving segments (approximately 12 hours), specifically curated for challenging long-tail scenarios that that are rare in daily life with an occurring frequency of less than 0.03%. Concretely, each segment in WOD-E2E includes the high-level routing information, ego states, and 360-degree camera views from 8 surrounding cameras. To evaluate the E2E driving performance on these long-tail situations, we propose a novel open-loop evaluation metric: Rater Feedback Score (RFS). Unlike conventional metrics that measure the distance between predicted way points and the logs, RFS measures how closely the predicted trajectory matches rater-annotated trajectory preference labels. We have released rater preference labels for all WOD-E2E validation set segments, while the held out test set labels have been used for the 2025 WOD-E2E Challenge. Through our work, we aim to foster state of the art research into generalizable, robust, and safe end-to-end autonomous driving agents capable of handling complex real-world situations.
arXiv:2510.26125v3 Announce Type: replace-cross
Abstract: Vision-based end-to-end (E2E) driving has garnered significant interest in the research community due to its scalability and synergy with multimodal large language models (MLLMs). However, current E2E driving benchmarks primarily feature nominal scenarios, failing to adequately test the true potential of these systems. Furthermore, existing open-loop evaluation metrics often fall short in capturing the multi-modal nature of driving or effectively evaluating performance in long-tail scenarios. To address these gaps, we introduce the Waymo Open Dataset for End-to-End Driving (WOD-E2E). WOD-E2E contains 4,021 driving segments (approximately 12 hours), specifically curated for challenging long-tail scenarios that that are rare in daily life with an occurring frequency of less than 0.03%. Concretely, each segment in WOD-E2E includes the high-level routing information, ego states, and 360-degree camera views from 8 surrounding cameras. To evaluate the E2E driving performance on these long-tail situations, we propose a novel open-loop evaluation metric: Rater Feedback Score (RFS). Unlike conventional metrics that measure the distance between predicted way points and the logs, RFS measures how closely the predicted trajectory matches rater-annotated trajectory preference labels. We have released rater preference labels for all WOD-E2E validation set segments, while the held out test set labels have been used for the 2025 WOD-E2E Challenge. Through our work, we aim to foster state of the art research into generalizable, robust, and safe end-to-end autonomous driving agents capable of handling complex real-world situations. Read More
Planning Agents on an Ego-Trip: Leveraging Hybrid Ego-Graph Ensembles for Improved Tool Retrieval in Enterprise Task Planningcs.AI updates on arXiv.org arXiv:2508.05888v2 Announce Type: replace
Abstract: Effective tool pre-selection via retrieval is essential for AI agents to select from a vast array of tools when identifying and planning actions in the context of complex user queries. Despite its central role in planning, this aspect remains underexplored in the literature. Traditional approaches rely primarily on similarities between user queries and tool descriptions, which significantly limits retrieval accuracy, specifically when handling multi-step user requests. To address these limitations, we propose a Knowledge Graph (KG)-based tool retrieval framework that captures the semantic relationships between tools and their functional dependencies. Our retrieval algorithm leverages ensembles of 1-hop ego tool graphs to model direct and indirect connections between tools, enabling more comprehensive and contextual tool selection for multi-step tasks. We evaluate our approach on a synthetically generated internal dataset across six defined user classes, extending previous work on coherent dialogue synthesis and tool retrieval benchmarks. Results demonstrate that our tool graph-based method achieves 91.85% tool coverage on the micro-average CompleteRecall metric, compared to 89.26% for re-ranked semantic-lexical hybrid retrieval, the strongest non-KG baseline in our experiments. These findings support our hypothesis that the structural information modeled in the graph provides complementary signals to pure similarity matching, particularly for queries requiring sequential tool composition.
arXiv:2508.05888v2 Announce Type: replace
Abstract: Effective tool pre-selection via retrieval is essential for AI agents to select from a vast array of tools when identifying and planning actions in the context of complex user queries. Despite its central role in planning, this aspect remains underexplored in the literature. Traditional approaches rely primarily on similarities between user queries and tool descriptions, which significantly limits retrieval accuracy, specifically when handling multi-step user requests. To address these limitations, we propose a Knowledge Graph (KG)-based tool retrieval framework that captures the semantic relationships between tools and their functional dependencies. Our retrieval algorithm leverages ensembles of 1-hop ego tool graphs to model direct and indirect connections between tools, enabling more comprehensive and contextual tool selection for multi-step tasks. We evaluate our approach on a synthetically generated internal dataset across six defined user classes, extending previous work on coherent dialogue synthesis and tool retrieval benchmarks. Results demonstrate that our tool graph-based method achieves 91.85% tool coverage on the micro-average CompleteRecall metric, compared to 89.26% for re-ranked semantic-lexical hybrid retrieval, the strongest non-KG baseline in our experiments. These findings support our hypothesis that the structural information modeled in the graph provides complementary signals to pure similarity matching, particularly for queries requiring sequential tool composition. Read More
Impact of Layer Norm on Memorization and Generalization in Transformerscs.AI updates on arXiv.org arXiv:2511.10566v1 Announce Type: cross
Abstract: Layer Normalization (LayerNorm) is one of the fundamental components in transformers that stabilizes training and improves optimization. In recent times, Pre-LayerNorm transformers have become the preferred choice over Post-LayerNorm transformers due to their stable gradient flow. However, the impact of LayerNorm on learning and memorization across these architectures remains unclear. In this work, we investigate how LayerNorm influences memorization and learning for Pre- and Post-LayerNorm transformers. We identify that LayerNorm serves as a key factor for stable learning in Pre-LayerNorm transformers, while in Post-LayerNorm transformers, it impacts memorization. Our analysis reveals that eliminating LayerNorm parameters in Pre-LayerNorm models exacerbates memorization and destabilizes learning, while in Post-LayerNorm models, it effectively mitigates memorization by restoring genuine labels. We further precisely identify that early layers LayerNorm are the most critical over middle/later layers and their influence varies across Pre and Post LayerNorm models. We have validated it through 13 models across 6 Vision and Language datasets. These insights shed new light on the role of LayerNorm in shaping memorization and learning in transformers.
arXiv:2511.10566v1 Announce Type: cross
Abstract: Layer Normalization (LayerNorm) is one of the fundamental components in transformers that stabilizes training and improves optimization. In recent times, Pre-LayerNorm transformers have become the preferred choice over Post-LayerNorm transformers due to their stable gradient flow. However, the impact of LayerNorm on learning and memorization across these architectures remains unclear. In this work, we investigate how LayerNorm influences memorization and learning for Pre- and Post-LayerNorm transformers. We identify that LayerNorm serves as a key factor for stable learning in Pre-LayerNorm transformers, while in Post-LayerNorm transformers, it impacts memorization. Our analysis reveals that eliminating LayerNorm parameters in Pre-LayerNorm models exacerbates memorization and destabilizes learning, while in Post-LayerNorm models, it effectively mitigates memorization by restoring genuine labels. We further precisely identify that early layers LayerNorm are the most critical over middle/later layers and their influence varies across Pre and Post LayerNorm models. We have validated it through 13 models across 6 Vision and Language datasets. These insights shed new light on the role of LayerNorm in shaping memorization and learning in transformers. Read More
Bridging LMS and generative AI: dynamic course content integration (DCCI) for enhancing student satisfaction and engagement via the ask ME assistantcs.AI updates on arXiv.org arXiv:2504.03966v2 Announce Type: replace-cross
Abstract: Integration of Large Language Models (LLMs) with Learning Management Systems (LMSs) can enhance task automation and accessibility in education. However, hallucination where LLMs generate inaccurate or misleading information remains a challenge. This study introduces the Dynamic Course Content Integration (DCCI) mechanism, which dynamically retrieves course content from Canvas LMS and structures it within an LLM’s context window via prompt engineering, enabling the LLM-powered assistant, Ask ME, to deliver context-aware, curriculum-aligned responses while mitigating hallucinations. A mixed-methods pilot study grounded in Self-Determination Theory (autonomy, competence) and the Technology Acceptance Model (perceived usefulness, ease of use) evaluated DCCI’s effectiveness with 120 first-year programming students at E”otv”os Lor’and University. The course focused on foundational programming patterns in C#, including writing program specifications. We analyzed 14,746 logged interactions and a post-course survey completed by 101 students. User satisfaction was measured via a 5-point Likert scale (turn-level ratings), while the survey assessed usability, engagement, and ethical concerns. Results indicated high satisfaction (mean 4.65/5) and strong recognition of Ask ME’s ability to provide timely, contextually relevant answers to administrative and course-related queries. 78.06% agreed that Ask ME’s Canvas integration reduced platform switching, improving usability, engagement, comprehension, and topic exploration. Many students reported reduced hesitation to ask questions and increased motivation for self-directed learning, though concerns about over-reliance on AI and reduced student-teacher interaction emerged. This study demonstrates that DCCI enhances LLM reliability, student satisfaction, and engagement in AI-driven educational automation, while highlighting the importance of balancing
arXiv:2504.03966v2 Announce Type: replace-cross
Abstract: Integration of Large Language Models (LLMs) with Learning Management Systems (LMSs) can enhance task automation and accessibility in education. However, hallucination where LLMs generate inaccurate or misleading information remains a challenge. This study introduces the Dynamic Course Content Integration (DCCI) mechanism, which dynamically retrieves course content from Canvas LMS and structures it within an LLM’s context window via prompt engineering, enabling the LLM-powered assistant, Ask ME, to deliver context-aware, curriculum-aligned responses while mitigating hallucinations. A mixed-methods pilot study grounded in Self-Determination Theory (autonomy, competence) and the Technology Acceptance Model (perceived usefulness, ease of use) evaluated DCCI’s effectiveness with 120 first-year programming students at E”otv”os Lor’and University. The course focused on foundational programming patterns in C#, including writing program specifications. We analyzed 14,746 logged interactions and a post-course survey completed by 101 students. User satisfaction was measured via a 5-point Likert scale (turn-level ratings), while the survey assessed usability, engagement, and ethical concerns. Results indicated high satisfaction (mean 4.65/5) and strong recognition of Ask ME’s ability to provide timely, contextually relevant answers to administrative and course-related queries. 78.06% agreed that Ask ME’s Canvas integration reduced platform switching, improving usability, engagement, comprehension, and topic exploration. Many students reported reduced hesitation to ask questions and increased motivation for self-directed learning, though concerns about over-reliance on AI and reduced student-teacher interaction emerged. This study demonstrates that DCCI enhances LLM reliability, student satisfaction, and engagement in AI-driven educational automation, while highlighting the importance of balancing Read More
Differentiating between human-written and AI-generated texts using linguistic features automatically extracted from an online computational toolcs.AI updates on arXiv.org arXiv:2407.03646v3 Announce Type: replace-cross
Abstract: While extensive research has focused on ChatGPT in recent years, very few studies have systematically quantified and compared linguistic features between human-written and Artificial Intelligence (AI)-generated language. This study aims to investigate how various linguistic components are represented in both types of texts, assessing the ability of AI to emulate human writing. Using human-authored essays as a benchmark, we prompted ChatGPT to generate essays of equivalent length. These texts were analyzed using Open Brain AI, an online computational tool, to extract measures of phonological, morphological, syntactic, and lexical constituents. Despite AI-generated texts appearing to mimic human speech, the results revealed significant differences across multiple linguistic features such as consonants, word stress, nouns, verbs, pronouns, direct objects, prepositional modifiers, and use of difficult words among others. These findings underscore the importance of integrating automated tools for efficient language assessment, reducing time and effort in data analysis. Moreover, they emphasize the necessity for enhanced training methodologies to improve the capacity of AI for producing more human-like text.
arXiv:2407.03646v3 Announce Type: replace-cross
Abstract: While extensive research has focused on ChatGPT in recent years, very few studies have systematically quantified and compared linguistic features between human-written and Artificial Intelligence (AI)-generated language. This study aims to investigate how various linguistic components are represented in both types of texts, assessing the ability of AI to emulate human writing. Using human-authored essays as a benchmark, we prompted ChatGPT to generate essays of equivalent length. These texts were analyzed using Open Brain AI, an online computational tool, to extract measures of phonological, morphological, syntactic, and lexical constituents. Despite AI-generated texts appearing to mimic human speech, the results revealed significant differences across multiple linguistic features such as consonants, word stress, nouns, verbs, pronouns, direct objects, prepositional modifiers, and use of difficult words among others. These findings underscore the importance of integrating automated tools for efficient language assessment, reducing time and effort in data analysis. Moreover, they emphasize the necessity for enhanced training methodologies to improve the capacity of AI for producing more human-like text. Read More
New prediction breakthrough delivers results shockingly close to realityArtificial Intelligence News — ScienceDaily Researchers have created a prediction method that comes startlingly close to real-world results. It works by aiming for strong alignment with actual values rather than simply reducing mistakes. Tests on medical and health data showed it often outperforms classic approaches. The discovery could reshape how scientists make reliable forecasts.
Researchers have created a prediction method that comes startlingly close to real-world results. It works by aiming for strong alignment with actual values rather than simply reducing mistakes. Tests on medical and health data showed it often outperforms classic approaches. The discovery could reshape how scientists make reliable forecasts. Read More
Visa builds AI commerce infrastructure for the Asia Pacific’s 2026 PilotAI News When Visa unveiled its Intelligent Commerce platform for Asia Pacific on November 12, it wasn’t just launching another payment feature—it was building AI commerce infrastructure to solve a crisis most merchants haven’t noticed yet: their websites are being flooded by AI agents, and there’s no reliable way to tell which ones are legitimate shoppers and which are malicious bots.
The post Visa builds AI commerce infrastructure for the Asia Pacific’s 2026 Pilot appeared first on AI News.
When Visa unveiled its Intelligent Commerce platform for Asia Pacific on November 12, it wasn’t just launching another payment feature—it was building AI commerce infrastructure to solve a crisis most merchants haven’t noticed yet: their websites are being flooded by AI agents, and there’s no reliable way to tell which ones are legitimate shoppers and which are malicious bots.
The post Visa builds AI commerce infrastructure for the Asia Pacific’s 2026 Pilot appeared first on AI News. Read More
The Kraken ransomware, which targets Windows, Linux/VMware ESXi systems, is testing machines to check how fast it can encrypt data without overloading them. […] Read More
US government agencies are warning that the Akira ransomware operation has been spotted encrypting Nutanix AHV virtual machines in attacks. […] Read More
