Agent-ValueBench is the first dedicated benchmark for agent values, showing they diverge from LLM values, form a homogeneous 'Value Tide' across models, and bend under harnesses and skill steering.
arXiv preprint arXiv:2510.04550 , year=
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.AI 4years
2026 4verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
ComplexMCP benchmark shows top LLM agents achieve under 60% success on dynamic interdependent tool tasks versus 90% for humans, due to tool retrieval saturation, over-confidence, and strategic defeatism.
A hybrid deterministic-plus-semantic interception layer for continuous task-based authorization of multi-turn LLM agent tool invocations, with new multi-turn datasets and initial experiments.
CMBAgent achieves high accuracy on well-specified astrophysical tasks with context but generates silent, plausible-yet-incorrect outputs on reasoning-challenging problems, with no self-diagnosis of inconsistencies.
citing papers explorer
-
Agent-ValueBench: A Comprehensive Benchmark for Evaluating Agent Values
Agent-ValueBench is the first dedicated benchmark for agent values, showing they diverge from LLM values, form a homogeneous 'Value Tide' across models, and bend under harnesses and skill steering.
-
ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox
ComplexMCP benchmark shows top LLM agents achieve under 60% success on dynamic interdependent tool tasks versus 90% for humans, due to tool retrieval saturation, over-confidence, and strategic defeatism.
-
Hybrid Inspection and Task-Based Access Control in Zero-Trust Agentic AI
A hybrid deterministic-plus-semantic interception layer for continuous task-based authorization of multi-turn LLM agent tool invocations, with new multi-turn datasets and initial experiments.
-
Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflows
CMBAgent achieves high accuracy on well-specified astrophysical tasks with context but generates silent, plausible-yet-incorrect outputs on reasoning-challenging problems, with no self-diagnosis of inconsistencies.