Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems
arXiv:2610.12822v1 Announce Type: new Abstract: Multi-agent systems are increasingly used to solve coding tasks by coordinating agents that share code and plans. These agents are often optimized with reinforcement learning (RL) using automated evaluators, but bypassing evaluation can earn reward wi…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-10-12 04:00 · arXiv cs.AI
Reward Hacking as a Transmissible Strategy in Multi-Agent Coding Systems