LegalSearch-R1 trains a 7B agent via RL on multi-period legal data with hybrid RAG/web search to improve temporal consistency, reporting 12.9-29.8% gains over SOTA and 57.7-80.3% on consistency metrics across 13 tasks.
InProceedings of the 38th AAAI Conference on Arti- ficial Intelligence, pages 18642–18650
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CL 2years
2026 2representative citing papers
citing papers explorer
-
Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning
LegalSearch-R1 trains a 7B agent via RL on multi-period legal data with hybrid RAG/web search to improve temporal consistency, reporting 12.9-29.8% gains over SOTA and 57.7-80.3% on consistency metrics across 13 tasks.
- Fine-grained Claim-level RAG Benchmark for Law