[Submitted on 5 Jun 2026 (v1), last revised 18 Oct 2026 (this version, v2)]
Abstract:Does high reward indicate productive coordination among language-model agents sharing resources? We examine this question in dining philosophers, where instances of the same model must acquire shared forks to eat. We evaluate seven model conditions across 630 episodes at five, ten, and fifteen philosophers, measuring scalar reward, deadlock, and meal throughput. At five philosophers, Mistral-Small 24B receives mean reward 0.827 while producing no meals. The reward decomposition explains this mismatch: avoiding deadlock earns a bonus without requiring meal production. To assess a policy trained with this reward, we compare the final checkpoint from a single Qwen3-14B group relative policy optimization (GRPO) training run with its base model. At five philosophers, the trained model has lower throughput (0.008 versus 0.020) and a higher deadlock rate in point estimates. Differences in mean episode reward are not statistically significant at any evaluated philosopher count. These findings show that the evaluated reward can assign high scores without task progress and support reporting behavioral measures alongside reward when comparing models and evaluating fine-tuned policies.
Submission history
From: Prashanth BusiReddyGari [view email]
[v1] Fri, 5 Jun 2026 21:13:14 UTC (2,159 KB)
[v2] Sun, 18 Oct 2026 23:16:16 UTC (2,040 KB)
