Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems
Paper • 2609.39050 • Published • 18
AI & ML interests
Factuality, reasoning, alignment, LLM applications
Recent Activity
View all activity
Papers
SchemeArena: Factorized Stress Testing of Scheming in LLM Agents
MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning
mkhalifa
authored a
paper 6 days ago
JieRuan
submitted a
paper to Daily Papers about 1 month ago
Ayoung01
authored 3
papers 3 months ago
MET: Theory-Grounded and Culture-Aware Multilingual Moral Reasoning
Paper • 2607.11736 • Published • 8
LiveOIBench: Can Large Language Models Outperform Human Contestants in Informatics Olympiads?
Paper • 2510.09595 • Published • 2
Logit Arithmetic Elicits Long Reasoning Capabilities Without Training
Paper • 2507.12759 • Published
Add paper link, code link, and task categories
#2 opened 3 months ago
by 
nielsr
Ayoung01
updated a
dataset 3 months ago
Ayoung01
updated 11
models 3 months ago
launch/MET-D-Gemma3-4B-en-only
Text Generation • 4B • Updated • 15
launch/MET-D-Gemma3-4B
Text Generation • 4B • Updated • 21
launch/MET-D-Qwen3-8B-en-only
Text Generation • 8B • Updated • 27
launch/MET-D-Qwen3-8B
Text Generation • 8B • Updated • 28
launch/MET-D-Qwen3-4B-zh-only
Text Generation • 4B • Updated • 19
launch/MET-D-Qwen3-4B-ms-only
Text Generation • 4B • Updated • 14
launch/MET-D-Qwen3-4B-ko-only
Text Generation • 4B • Updated • 22
launch/MET-D-Qwen3-4B-hi-only
Text Generation • 4B • Updated • 10
launch/MET-D-Qwen3-4B-es-only
Text Generation • 4B • Updated • 14
launch/MET-D-Qwen3-4B-en-only
Text Generation • 4B • Updated • 19
launch/MET-D-Qwen3-4B
Text Generation • 4B • Updated • 17
Ayoung01
updated a
collection 3 months ago
Ayoung01
submitted a
paper to Daily Papers 3 months ago