💡 AI Assistants - ABQ_Work · Scour

VESTA: A Fully Automated Scenario Generation and Safety Evaluation Framework for LLM Agents

🧠LLMs Academic

DeployBench: Benchmarking LLM Agents for Research Artifact Deployment

🧠LLMs Academic

AGENTSERVESIM: A Hardware-aware Simulator for Multi-Turn LLM Agent Serving

🧠LLMs Academic

Agentic Monte Carlo: Simulating Reinforcement Learning for Black-Box Agents

🤖AI Coding Tools Academic

LLM Agent-Assisted Reverse Engineering with Quantitative Readability Metrics

🧠LLMs Academic

TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents

🤖AI Coding Tools Academic

Provably Auditable and Safe LLM Agents from Human-Authored Ontologies

🧠LLMs Academic

SecureClaw: Clawing Back Control of LLM Agents

🧠LLMs Academic

Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps

🧠LLMs Academic

Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agents

🧠LLMs Academic

MemToolAgent overview with a simple restaurant booking scenario where the agent retrieves similar memories, receives feedback on an invalid time format, and generates a reflection to update its memory

🧠LLMs Academic

Will the Agent Recuse Itself? Measuring LLM-Agent Compliance with In-Band Access-Deny Signals

🛡️Security Advisories Academic

Memory Beyond Recall: A Dual-Process Cognitive Memory System for Self-Evolving LLM Agents

🧠LLMs Academic

REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Traces

🧠LLMs Academic

From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents

🛡️Memory Safety Academic

Causal Agent Replay: Counterfactual Attribution for LLM-Agent Failures

🧠LLMs Academic

Plan First, Judge Later, Run Better: A DMAIC-Inspired Agentic System for Industrial Anomaly Detection

🏛️Software Architecture Academic

Decision-Aware Memory Cards: Counterfactual-Inspired Context Selection and Compression for Tool-Using LLM Agents

🧠LLMs Academic

OpenSkill: Open-World Self-Evolution for LLM Agents

🧠LLMs Academic

Caught in the Act(ivation): Toward Pre-Output and Multi-Turn Detection of Credential Exfiltration by LLM Agents

🧠LLMs Academic

Log in to enable infinite scrolling