Oleksandr Karpov

semsorock

2 4

·

AI & ML interests

None yet

Recent Activity

updated a Space about 7 hours ago

semsorock/repro-when-agents-go-rogue-acmas

published a Space about 7 hours ago

semsorock/repro-when-agents-go-rogue-acmas

updated a bucket about 7 hours ago

semsorock/repro-when-agents-go-rogue-acmas-artifacts

View all activity

Organizations

semsorock 's Spaces 4

Repro - When Agents Go Rogue: Activation-Based Detection of Malicious Behaviors in Multi-Agent Systems

Detect rogue agent behaviors from system logs

Repro: CyberJurors: A Multi-Agent Simulation Task for E-Commerce Disputes Verdict

Explore simulation logs and collaborate with an AI agent

Repro: AdvEvo-MARL: Shaping Internalized Safety through Adversarial Co-Evolution in Multi-Agent Reinforcement Learning

Browse experiment logs and collaborate with an AI agent

Repro - The Value of Variance - Mitigating Debate Collapse in Multi-Agent Systems via Uncertainty-Driven Policy Optimization

Explore experiment logs and sync with your coding agent