一作ACL 2026Poster· Natural Language Processing
Agentic Rubrics as Contextual Verifiers for SWE Agents
Mohit Raghavendra · Anisha Gunjal · Bing Liu · Yunzhong He
摘要
Verification is critical for improving agents: it provides the reward signal for Reinforcement Learning and enables inference-time gains through Test-Time Scaling (TTS). Despite its importance, verification in software engineering (SWE) agent settings often relies on code execution, which can be...