Fetching from the wire…
01
02
03
04
05
06
07
08
Agents2026-08-11 · source-backed
arXiv 2608.09902 wraps all 22 boss encounters of Dark Souls: Remastered in a containerized Gymnasium-style benchmark where each step is a real action against the running game. On DSLE-5, an expert system and an evolutionary baseline beat only the tutorial boss (63% and 43% peak win rates). PPO and DQN showed no measurable learning at all, topping out at 0.33% on the tutorial boss and 0% everywhere else. A benchmark with genuine headroom instead of one saturated on release is rare enough to note.
Each link below shares sources, entities, or timing with this story.
GRPO competes with PPO / Shared entity: PPO / Same source domain / Shared topic / Earlier coverage
Linked by a graph relationship (GRPO competes with PPO); both cover PPO; reported by the same outlet (arxiv.org).
Shared entity: PPO / Same source domain / Shared topic / Earlier coverage
Both cover PPO; reported by the same outlet (arxiv.org); overlapping topics (action, agent, each).
GRPO competes with PPO / Same source domain / Shared topic
Linked by a graph relationship (GRPO competes with PPO); reported by the same outlet (arxiv.org); overlapping topics (action, agent, benchmark).
Same source domain / Shared topic / Tension
Reported by the same outlet (arxiv.org); overlapping topics (against, agent, baseline, beat); pushes against this story (against).
Reported by the same outlet (arxiv.org); overlapping topics (agent, baseline, beat, benchmark); pushes against this story (versus).
GRPO competes with PPO / Same source domain / Shared topic
Linked by a graph relationship (GRPO competes with PPO); reported by the same outlet (arxiv.org); overlapping topics (agent, beat).
Linked by a graph relationship (GRPO competes with PPO); reported by the same outlet (arxiv.org); overlapping topics (beat, benchmark).
Linked by a graph relationship (GRPO competes with PPO); reported by the same outlet (arxiv.org); overlapping topics (agent, learning).