Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning

arXiv:2605.25920 · cs.CL, cs.AI · Submitted 2026-05-25 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-05-25

Updated: 2026-09-19

Comments: Accepted by EMNLP NLLP 2026

Code: https://github.com/AlexFanw/LegalSearch-R1

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• RAG — 55× in this paper · explained in 3 episodes
• Benchmark — 18× in this paper · explained in 2 episodes
• Reinforcement Learning — 14× in this paper · explained in 4 episodes
• Agentic Search — 13× in this paper · explained in 1 episode
• Consistency — 13× in this paper · explained in 3 episodes
• Temporal consistency — 12× in this paper · explained in 2 episodes
• Generalization — 7× in this paper · explained in 13 episodes
• Legal Article Recitation — 6× in this paper
• Accuracy — 4× in this paper · explained in 1 episode
• Adam — 4× in this paper · explained in 2 episodes
• Commentary — 4× in this paper · explained in 2 episodes
• Core — 4× in this paper · explained in 2 episodes
• GRPO — 4× in this paper · explained in 6 episodes
• Legal Case Analysis — 4× in this paper
• Large Language Models (LLMs) — 3× in this paper · explained in 6 episodes
• Analyzer — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Certified Public Accountant — 2× in this paper
• Criminal Charge Prediction — 2× in this paper
• Fine-Tuning — 2× in this paper · explained in 5 episodes
• Generalizability — 2× in this paper · explained in 6 episodes
• Knowledge Question Answering — 2× in this paper
• LLM judge — 2× in this paper · explained in 2 episodes
• Legal Article Prediction — 2× in this paper
• Provenance — 2× in this paper · explained in 3 episodes
• Adaptability — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Embeddings — 1× in this paper · explained in 2 episodes
• Entropy Collapse — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• Information Gain — 1× in this paper · explained in 2 episodes
• Knowledge Graph — 1× in this paper · explained in 7 episodes
• Legal Basic Knowledge — 1× in this paper
• Mixture of Experts — 1× in this paper · explained in 2 episodes
• National Judicial Examination — 1× in this paper
• Patent Agent Examination — 1× in this paper
• Prison Term Prediction — 1× in this paper
• Professional Fundamentals Examination — 1× in this paper
• Reward Function — 1× in this paper · explained in 2 episodes
• Temporal Reasoning — 1× in this paper · explained in 2 episodes
• Tokenization — 1× in this paper · explained in 2 episodes
• Trace — 1× in this paper · explained in 2 episodes
• Unified National Graduate Entrance Examination — 1× in this paper

Sources

• GPT-4 Technical Report
• SaulLM-7B: A pioneering Large Language Model for Law
• Open Deep Search: Democratizing Search with Open-source Reasoning Agents
• Unilaw-R1: A Large Language Model for Legal Reasoning with Reinforcement Learning and Iterative Inference
• ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning
• Chatlaw: A Multi-Agent Legal Assistant based on a Role-Aligned Mixture-of-Experts Architecture
• Legal$\Delta$: Enhancing Legal Reasoning in LLMs via Reinforcement Learning with Chain-of-Thought Guided Information Gain
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• DeepSeek-V3 Technical Report
• DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping
• LawBench: Benchmarking Legal Knowledge of Large Language Models
• Retrieval-Augmented Generation for Large Language Models: A Survey
• LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models
• Lawyer LLaMA Technical Report
• Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• LRAGE: Legal Retrieval Augmented Generation Evaluation Tool
• OpenAI o1 System Card
• Qwen2.5 Technical Report
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering