arXiv cs.MA· Justin Downes, Robby Milletich, Newel Hirst·· 11 小时前AI 评分31
同一方法，不同任务：Bitter Lesson 在社会模拟中并不授权什么
Same Method, Different Task: What the Bitter Lesson Does Not License in Social Simulation
AI 导读
一篇被 NeurIPS 2026 SocialAgent Workshop 接收的论文指出，Sutton 的 Bitter Lesson 在每一个案例中都是让通用方法在同一任务上与领域工程竞争，而社会模拟却跨任务替换，用为预测文本优化的产物取代手工构建的智能体。
正文 · 原文
Abstract:The bitter lesson holds that general methods leveraging computation defeat hand-encoded domain knowledge. We argue it carries a condition its popular reading omits: in every case Sutton cites, the general method was scaled against the same task the domain engineering was solving. Social simulation substituted across tasks instead, replacing hand-built agents with an artifact optimized for predicting text. The move is bitter-lesson-shaped, but the lesson does not license it. Prediction is a solitary act: the predictor bears no consequences from the interaction it models. Cooperation, defection, and norm enforcement are phenomena of interested parties; they do not exist for a disinterested observer at any scale. What is missing is not emergence, which LLM populations already show, but stakes. We show that several anomalies reported in prior work (excess cooperation that predates alignment training, collective agreement without individual fidelity, and population homogeneity) follow from this account. A 540-agent pilot with pre-specified hypotheses, which tests sensitivity to persistent consequences rather than cooperation, finds that consequences reshape strategies in two of three model families but never produce human-like heterogeneity. We argue for mixed-motive settings that shape agents rather than only test them, and ask whether agents should be pretrained differently from predictors.
| Comments: | Accepted at the SocialAgent Workshop, NeurIPS 2026 (non-archival). 15 pages, 5 figures |
| Subjects: | Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2611.05717 [cs.MA] |
| (or arXiv:2611.05717v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2611.05717 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Justin Downes [view email]
[v1]
Tue, 3 Nov 2026 22:42:46 UTC (63 KB)
来源：arXiv cs.MA · arxiv.org