Researchers from Penn, Renmin University and Microsoft Research built tasks from Go, Rust and C/C++ projects with hidden behavioral tests. Their blog reports RL on Qwen3.6-35B-A3B raised its ProgramBench pass rate from 13.7% to 24.0% in Claude Code, and a...
VQV Signal
RESEARCH
WATCH
TECHNICAL
ProgramLab: 1,261 hidden-source programs for training agents to rebuild software with RL
Researchers from Penn, Renmin University and Microsoft Research built tasks from Go, Rust and C/C++ projects with hidden behavioral tests. Their blog reports RL on Qwen3.6-35B-A3B raised its ProgramBench pass rate from 13.7% to 24.0% in Claude Code, and a...
Researchers from Penn, Renmin University and Microsoft Research built tasks from Go, Rust and C/C++ projects with hidden behavioral tests. Their blog reports RL on Qwen3.6-35B-A3B raised its ProgramBench pass rate from 13.7% to 24.0% in Claude Code, and a five-agent team from 17.2% to 25.0%. Original post on X...
VQV organizes public signals from inspectable sources. It does not independently verify the underlying report.
Signal Strength 88%
Technical label WATCH
Public Interest 24
Category RESEARCH
Reader Depth TECHNICAL
Signal Strength reflects source quality, relevance, freshness and evidence. Public Interest helps organize discovery; it is not proof of truth.
Public Interest components
Recognizable Entity Score 0
Practical Impact Score 8
Novelty Interest Score 70
Consequence Score 18
Curiosity Score 16
Shareability Score 42
VQV surfaced this signal because it is recent, relevant to Open Source LLMs, connected to Scobleizer News Pulse (X).
No login, cookies, social SDKs, or automatic posting.