arXiv:2605.08563v1 Announce Type: new Abstract: When an LLM agent fails a multi-step tool-augmented task and retries, the failed attempt typically remains in its context window -- contaminating the ne…
cyberintel.kalymoon.com · 21051 articles · updated every 4 hours · grows forever
arXiv:2605.08563v1 Announce Type: new Abstract: When an LLM agent fails a multi-step tool-augmented task and retries, the failed attempt typically remains in its context window -- contaminating the ne…
arXiv:2605.08549v1 Announce Type: new Abstract: Conversational AI is increasingly personalized around users' preferences, histories, goals, and knowledge, but much less around how users interpret and …
arXiv:2605.08545v1 Announce Type: new Abstract: Agent benchmarks typically report only final outcomes: pass or fail. This threatens evaluation credibility in three ways. First, scores may be inflated …
arXiv:2605.08538v1 Announce Type: new Abstract: Current LLM agents lack principled mechanisms for managing persistent memory across long interaction horizons. We present a biologically-grounded memory…
arXiv:2605.08533v1 Announce Type: new Abstract: Clinical decision-making in emergency medicine demands rapid, accurate diagnoses under uncertainty. Despite benchmark progress, evidence for LLMs as int…
arXiv:2605.08518v1 Announce Type: new Abstract: Competition retrospectives are useful when they explain what a leaderboard measured, how hidden evaluation changed conclusions, and which design pattern…
arXiv:2605.08516v1 Announce Type: new Abstract: Transparent decision-making is essential for traffic signal control (TSC) systems to earn public trust. However, traditional reinforcement learning-base…
arXiv:2605.08496v1 Announce Type: new Abstract: Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to hundreds of thousands of ex…
arXiv:2605.08480v1 Announce Type: new Abstract: Individuals with Alzheimer's disease (AD) and Alzheimer's disease-related dementia (ADRD) experience memory and thinking changes that impact their abili…
arXiv:2605.08472v1 Announce Type: new Abstract: The effectiveness of Reinforcement Learning (RL) in Large Language Models (LLMs) depends on the nature and diversity of the data used before and during …
arXiv:2605.08463v1 Announce Type: new Abstract: Autonomous AI agents are increasingly deployed in open social environments, yet the relationship between their configuration specifications and their em…
arXiv:2605.08448v1 Announce Type: new Abstract: Semi-supervised learning approaches have been investigated as a means to enhance the analysis of social media data in disaster management contexts. In t…
arXiv:2605.08445v1 Announce Type: new Abstract: AI models are increasingly deployed in live clinical environments where they must perform reliably across complex, high-stakes workflows that standard t…
A vulnerability was found in SAP Application Server ABAP for NetWeaver and ABAP Platform and classified as critical . Affected by this vulnerability is an unknown functionality. Such manipulation lead…
A vulnerability was found in SAP NetWeaver Application Server for ABAP and ABAP Platform . It has been classified as critical . Affected by this issue is some unknown functionality. Performing a manip…
A vulnerability was found in SAP Forecasting & Replenishment 702/712/713/714 . It has been declared as critical . This affects an unknown part. Executing a manipulation can lead to command injection. …
A vulnerability was found in SAP Commerce Cloud Configuration 2211-JDK21/COM_CLOUD 2211/HY_COM 2205 . It has been rated as very critical . This vulnerability affects unknown code. The manipulation lea…
A vulnerability categorized as problematic has been discovered in SAP Incentive and Commission Management up to SAP_APPL 618 . This issue affects some unknown processing. The manipulation results in m…
A vulnerability identified as problematic has been detected in SAP Financial Consolidation 1010 . Impacted is an unknown function. This manipulation causes denial of service. This vulnerability is tra…
A vulnerability labeled as problematic has been found in SAP NetWeaver Application Server ABAP . The affected element is an unknown function of the component Business Server Page . Such manipulation l…
A vulnerability marked as critical has been reported in SAP S4HANA AP_BAI 751 up to AP_BAI 758 . The impacted element is an unknown function. Performing a manipulation results in sql injection. This v…
A vulnerability described as critical has been identified in SAP Strategic Enterprise Management up to SEM-BW 605 . This affects an unknown function of the component Business Server Page . Executing a…
A vulnerability classified as critical has been found in SAP S4HANA Condition Maintenance up to 109 . This impacts an unknown function. The manipulation leads to missing authorization. This vulnerabil…
A vulnerability classified as problematic was found in SAP Business Server Pages Application 740/758 . Affected is an unknown function of the component TAF_APPLAUNCHER . The manipulation results in cr…