Handshake-AI-Research/deepswe-samples

Coding Agents Build for the Grader They Imagine, Not the User: Speculative Reward Hacking in DeepSWE

0

3 commits

updated Sep 23, 2026

See the code

See what people are saying

SourceMessageScoreDate

Speculative Reward Hacking in Coding Agents

I audited thousands of agent rollouts in DeepSWE-1.1. Over 80% contained reasoning about an imagined grader. Yet no grader/verifier is mentioned in prompts nor accessible to the agents. Agents reasoned things like: "Let me look at the problem from the grader's perspective" and referred to "hidden…

0

Sep 25, 2026

Contributors

jwmueller

2 commits

huiwengoh-hs

1 commits

Handshake-AI-Research/deepswe-samples

Coding Agents Build for the Grader They Imagine, Not the User: Speculative Reward Hacking in DeepSWE

0

3 commits

updated Sep 23, 2026

See the code

See what people are saying

SourceMessageScoreDate

Speculative Reward Hacking in Coding Agents

I audited thousands of agent rollouts in DeepSWE-1.1. Over 80% contained reasoning about an imagined grader. Yet no grader/verifier is mentioned in prompts nor accessible to the agents. Agents reasoned things like: "Let me look at the problem from the grader's perspective" and referred to "hidden…

0

Sep 25, 2026

Contributors

jwmueller

2 commits

huiwengoh-hs

1 commits