arxiv:2509.22799
Tom Lu
eigentom
ยท
AI & ML interests
MLLM, Generative AI, Agentic RL
Recent Activity
upvoted
a
paper
about 12 hours ago
GEM: A Gym for Agentic LLMs
upvoted
a
paper
about 12 hours ago
Language Models Can Learn from Verbal Feedback Without Scalar Rewards
upvoted
a
paper
about 12 hours ago
MCPMark: A Benchmark for Stress-Testing Realistic and Comprehensive MCP
Use
Organizations
models
0
None public yet
datasets
0
None public yet