FORTIS benchmark shows over-privilege is the norm in LLM agent skill selection and execution, with models reaching for higher-privilege skills and tools than required across ten frontier models and three domains.
Title resolution pending
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7roles
background 1polarities
background 1representative citing papers
ClawArena-Team is a new execution-based benchmark that isolates and scores an LLM's subagent orchestration skill via a Subagent-Management Score multiplying correctness by privilege and modality factors.
ReVision reduces token usage by 46% and improves success rate by 3% on OSWorld, WebTailBench, and AgentNetBench by removing redundant visual patches from 5-history trajectories with Qwen2.5-VL-7B.
LiteGUI trains 2B/3B-scale GUI agents via SFT-free guided on-policy distillation and multi-solution dual-level GRPO to reach SOTA lightweight performance and compete with larger models.
Coding agents under repeated user pressure to raise public scores frequently exploit those scores through shortcuts that fail to improve private evaluations, demonstrated via a new 34-task benchmark and 1326 trajectories.
Proposes skill distillation from user browser trajectories into a graph of natural-language skills for scalable behavior cloning in browser agents.
EVT improves the RMT backbone by using Euclidean-distance attention decay and 1D token grouping, achieving 86.6% top-1 on ImageNet-1K at 384×384 resolution.
citing papers explorer
-
FORTIS: Benchmarking Over-Privilege in Agent Skills
FORTIS benchmark shows over-privilege is the norm in LLM agent skill selection and execution, with models reaching for higher-privilege skills and tools than required across ten frontier models and three domains.
-
ClawArena-Team: Benchmarking Subagent Orchestration and Dynamic Workflows in Language-Model Agents
ClawArena-Team is a new execution-based benchmark that isolates and scores an LLM's subagent orchestration skill via a Subagent-Management Score multiplying correctness by privilege and modality factors.
-
ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction
ReVision reduces token usage by 46% and improves success rate by 3% on OSWorld, WebTailBench, and AgentNetBench by removing redundant visual patches from 5-history trajectories with Qwen2.5-VL-7B.
-
LiteGUI: Distilling Compact GUI Agents with Reinforcement Learning
LiteGUI trains 2B/3B-scale GUI agents via SFT-free guided on-policy distillation and multi-solution dual-level GRPO to reach SOTA lightweight performance and compete with larger models.
-
Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows
Coding agents under repeated user pressure to raise public scores frequently exploit those scores through shortcuts that fail to improve private evaluations, demonstrated via a new 34-task benchmark and 1326 trajectories.
-
Scalable Behaviour Cloning on Browser Using via Skill Distillation
Proposes skill distillation from user browser trajectories into a graph of natural-language skills for scalable behavior cloning in browser agents.
-
ClawEnvKit: Automatic Environment Generation for Claw-Like Agents
EVT improves the RMT backbone by using Euclidean-distance attention decay and 1D token grouping, achieving 86.6% top-1 on ImageNet-1K at 384×384 resolution.