Personal list
For You
A reading list shaped by the topics you follow and the papers you react to.
Following AgentFollowing LLMFollowing Reasoning
#1A Dual-Hypothesis Reasoning Framework for LLM GuardrailsMatches your interests in LLM, Reasoning.This framework could improve the safety and interpretability of LLMs, which is crucial for their deployment in sensitive applications.LLMReasoningSafetyInterpretabilityDaily score 71.7Topic fit LLM, Reasoning#2Beyond Fixed Benchmarks and Worst-Case Attacks: Dynamic Boundary Evaluation for Language ModelsMatches your interests in LLM.This approach could lead to more nuanced and informative evaluations of language models, highlighting specific capability gaps and improving model development.LLMEvaluationBenchmarkDaily score 71.1Topic fit LLM#3OSGuard: A Benchmark for Safety in Computer-Use AgentsMatches your interests in Agent.As AI agents increasingly perform complex tasks, ensuring their safety and reliability is crucial for real-world applications, making OSGuard a valuable tool for researchers and developers.AgentEvaluationBenchmarkSafetyDaily score 70.6Topic fit Agent#4SAFETY SENTRY: Context-Aware Human Intervention via EXECUTE-ASK-REFUSE RoutingMatches your interests in LLM, Agent.This approach could enhance the reliability and user experience of AI systems by reducing false alarms and improving safety in real-world applications.LLMAgentSafetyDaily score 69.3Topic fit LLM, Agent#5Learning to Configure Agentic AI SystemsMatches your interests in LLM, Agent, Reasoning.This approach could optimize computational resources and enhance the accuracy of AI systems by tailoring configurations to specific queries, addressing the limitations of static configurations.LLMAgentReasoningBenchmarkDaily score 68.0Topic fit LLM, Agent, Reasoning#6Beyond Component Testing: Validating Agentic AI SystemsMatches your interests in Agent.Understanding and validating the complex behaviors of agentic AI systems is crucial for their safe and trustworthy deployment in real-world applications.AgentEvaluationSafetySurveyDaily score 63.8Topic fit Agent#7Strategic Evaluation of Planning Strategies for LLM Agents in Cyber-Physical SystemsMatches your interests in LLM, Agent.Understanding how different planning architectures affect outcomes in cyber-physical systems can guide the development of more effective and reliable AI-driven control systems.LLMAgentEvaluationBenchmarkDaily score 62.6Topic fit LLM, Agent#8Rethinking Modality Reliability in Multimodal Sentiment Analysis with Incomplete ObservationsPicked from the daily list.Understanding and modeling modality reliability can significantly improve the performance of sentiment analysis systems in real-world scenarios where data is often incomplete.OtherDaily score 62.0From the wider daily list#9Reasoning as Pattern Matching: Shared Mechanisms in Human and LLM Everyday ReasoningMatches your interests in LLM, Reasoning.Understanding the similarities in reasoning errors between humans and LLMs can inform the development of more robust AI systems and improve our understanding of human cognition.LLMReasoningInterpretabilityDaily score 56.7Topic fit LLM, Reasoning#10Inverse-LLaVA: Rethinking Multimodal Alignment via Text-to-Vision MappingPicked from the daily list.Write-up coming soon.OtherDaily score 51.7From the wider daily list