Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
Paper • 2604.13602 • Published • 20
threadcup
threadcup
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 months ago
BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation upvoted a paper 3 months ago
TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World ScenariosOrganizations
None yet
upvoted a paper 1 day ago
upvoted 3
papers 3 months ago
BatCoder: Self-Supervised Bidirectional Code-Documentation Learning via Back-Translation
Paper • 2602.02554 • Published • 8
TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios
Paper • 2602.01675 • Published • 9
Controllable Memory Usage: Balancing Anchoring and Innovation in Long-Term Human-Agent Interaction
Paper • 2601.05107 • Published • 24