Behavioral Self-Rewarding 提升 SWE agent 训练效果
Penn State 与 Microsoft Research 提出 Behavioral Self-Rewarding，让 SWE agent 对自身轨迹两两比较生成有界偏好奖励，叠加在测试结果之上，解决二元测试奖励在整组全过或全挂时无对比度的问题。
// Behavioral Self-Rewarding for SWE agents //
It's standard practice to train SWE agents on binary test rewards.
This paper shows the problem with that. When every trajectory in a group passes, or every one fails, the reward has no contrast, and the group teaches nothing.
Researchers from Penn State and Microsoft Research propose Behavioral Self-Rewarding. The policy compares its own trajectories in pairs, and those preferences become small bounded rewards added on top of the test result.
The added rewards are bounded, so a self-judged preference can rank two passing trajectories but can never lift a failing one above a passing one.
No new environment interactions are needed. On SWE-bench Verified, Qwen3-14B improves from 32.1% to 34.7% average accuracy at a 400-step budget, and on SWE-bench-Live from 6.33% to 8.11%.
arxiv.org/abs/2610.12598
Chat with Paper: academy.dair.ai/papers/beyon…
来源：dair_ai · x.com