PXAI Audio Feed
27/03 16:02 dev.to

LLM Agents Should Never Execute Raw Commands

LLM agentscommand injectionprompt injectionbackend securitytext generationautomation risk
27/03 06:00 arxiv.org

AutoSAM: an Agentic Framework for Automating Input File Generation for the SAM Code with Multi-Modal Retrieval-Augmented Generation

AutoSAMSAM input generationLLM agentretrieval‑augmented generationmultimodal parsingreactor design
26/03 06:00 arxiv.org

Can LLM Agents Be CFOs? A Benchmark for Resource Allocation in Dynamic Enterprise Environments

LLM agentsCFO simulationresource allocationEnterpriseArenaenterprise benchmarkmacroeconomic signals
26/03 03:58 dev.to

Intent to Specs: Agentic Specification Protocol

agentic specification protocolbusiness analysisLLM agentstrinity frameworktask context constraintbridging intent
25/03 17:39 dev.to

Your Agent Hired Another Agent. The Output Was Garbage. The Money's Gone.

LLM agentsJSON outputpipeline failurerefund mechanismBotNodeopen source
24/03 16:05 takara.ai

MemCollab: Cross-Agent Memory Collaboration via Contrastive Trajectory Distillation

cross-agent memorycontrastive learningLLM agentsshared knowledgetrajectory distillationagent-agnostic memory
24/03 15:30 towardsdatascience.com

Production-Ready LLM Agents: A Comprehensive Framework for Offline Evaluation

LLM agentsoffline evaluationAI agent systemsperformance metricsreproducibilityAI safety
23/03 06:00 arxiv.org

A Subgoal-driven Framework for Improving Long-Horizon LLM Agents

LLM agentssubgoal decompositionlong-horizon planningreinforcement learningdynamic web navigationsparse rewards
19/03 12:32 dev.to

How to Use Agent Skills in Enterprise LLM Agent Systems

Enterprise AILLM agentsAgent SkillsDesktop AIBusiness process integrationWeb interface
19/03 12:32 dev.to

How to Use Agent Skills in Enterprise LLM Agent Systems

Enterprise AILLM agentsAgent SkillsDesktop AIBusiness process integrationWeb interface
Comments
Loading...
0