🧪 Agent Evaluation - sworddish · Scour

Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents

🌳Decision-Time Planning Academic

Less-relevant results

How Do You Handle False Positives in Automated Scans?

✓Formal Verification

hackernoon.com·

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation

💬LLMs Academic

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

💬LLMs Academic

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

✓Formal Verification Academic

ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity

🌳Decision-Time Planning Academic

arxiv.org··Hacker News

Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution

💬LLMs Academic

The Cold-Start Safety Gap in LLM Agents

💬LLMs Academic

HIPIF: Hierarchical Planning and Information Folding for Long-Horizon LLM Agent Learning

🌳Decision-Time Planning Academic

Autoregressive Diffusion World Models for Off-Policy Evaluation of LLM Agents

💬LLMs Academic

Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops

🃏Imperfect Information Games Academic

Less Context, Better Agents: Efficient Context Engineering for Long-Horizon Tool-Using LLM Agents

💬LLMs Academic

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

💬LLMs Academic

DeployBench: Benchmarking LLM Agents for Research Artifact Deployment

💬LLMs Academic

EEVEE: Towards Test-time Prompt Learning in the Real World for Self-Improving Agents

🃏Imperfect Information Games Academic

Silent Failure in LLM Agent Systems: The Entropy Principle and the Inevitable Disorder of Autonomous Agents

🃏Imperfect Information Games Academic

Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full History

💬LLMs Academic

SecureClaw: Clawing Back Control of LLM Agents

💬LLMs Academic

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

🃏Imperfect Information Games Academic

Assessing Automated Prompt Injection Attacks in Agentic Environments

🃏Imperfect Information Games Academic

Log in to enable infinite scrolling