SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
Paper
• 2602.12670 • Published
• 54
University of Southern California
university
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Are LLM Decisions Faithful to Verbal Confidence?
LYNX: Learning Dynamic Exits for Confidence-Controlled Reasoning
Hudx111
authored a paper 1 day ago
Hudx111
authored a paper 7 days ago
Who runs this page?
🔥 1
2
#1 opened 18 days ago
by
johntzwei
Who runs this page?
🔥 1
2
#1 opened 18 days ago
by
johntzwei
Who runs this page?
🔥 1
2
#1 opened 18 days ago
by
johntzwei
Who runs this page?
🔥 1
2
#1 opened 18 days ago
by
johntzwei
deqing
submitted a paper to Daily Papers about 2 months ago
farukakgul
submitted a paper to Daily Papers 3 months ago
wangyz1999
authored 2 papers 4 months ago
johntzwei
authored a paper 7 months ago
skricheli2
authored a paper 9 months ago
Dhananjay99
authored a paper 9 months ago
mattf1n
authored 6 papers 10 months ago
Teaching Models to Understand (but not Generate) High-risk Data
Paper
• 2505.03052 • Published
• 6
Closing the Curious Case of Neural Text Degeneration
Paper
• 2310.01693 • Published
Attentiveness to Answer Choices Doesn't Always Entail High QA Accuracy
Paper
• 2305.14596 • Published
• 1
What Makes Instruction Learning Hard? An Investigation and a New Challenge in a Synthetic Environment
Paper
• 2204.09148 • Published
Logits of API-Protected LLMs Leak Proprietary Information
Paper
• 2403.09539 • Published
• 1
Decomposed Prompting: A Modular Approach for Solving Complex Tasks
Paper
• 2210.02406 • Published
• 1