Recent search-augmented LLMs trained with reinforcement learning (RL) can interleave searching and reasoning for multi-hop reasoning tasks.However, they face two critical failure modes as the accumulating context becomes flooded with both crucial evidence and irrelevant information: (1) ineffective search chain construction that produces incorrect queries or omits retrieval of critical information, and (2) reasoning hijacking by peripheral evidence that causes models to misidentify distractors as valid evidence.To address these challenges, we propose D 2 PLAN, a Dual-agent Dynamic global Planning paradigm for complex retrieval-augmented reasoning.D 2 PLAN operates through the collaboration of a Reasoner and a Purifier: the Reasoner constructs explicit global plans during reasoning and dynamically adapts them based on retrieval feedback; the Purifier assesses retrieval relevance and condenses key information for the Reasoner.We further introduce a two-stage training framework consisting of supervised finetuning (SFT) cold-start on synthesized trajectories and RL with plan-oriented rewards to teach LLMs to master the D 2 PLAN paradigm.Extensive experiments demonstrate that D 2 PLAN enables more coherent multi-step reasoning and stronger resilience to irrelevant information, thereby achieving superior performance on challenging QA benchmarks.

Interpreting the law is always essential for the law to adapt to the ever-changing society.It is a critical and challenging task even for legal practitioners, as it requires meticulous and professional annotations and summarizations by legal experts, which are admittedly timeconsuming and expensive to collect at scale.To alleviate the burden on legal experts, we propose a method for automated legal interpretation.Specifically, by emulating doctrinal legal research, we introduce a novel framework, ATRIE, to address Legal Concept Interpretation, a typical task in legal interpretation.ATRIE utilizes large language models (LLMs) to AuTomatically Retrieve conceptrelated information, Interpret legal concepts, and Evaluate generated interpretations, eliminating dependence on legal experts.ATRIE comprises a legal concept interpreter and a legal concept interpretation evaluator.The interpreter uses LLMs to retrieve relevant information from previous cases and interpret legal concepts.The evaluator uses performance changes on Legal Concept Entailment, a downstream task we propose, as a proxy of interpretation quality.Automated and multifaceted human evaluations indicate that the quality of our interpretations is comparable to those written by legal experts, with superior comprehensiveness and readability.Although there remains a slight gap in accuracy, it can already assist legal practitioners in improving the efficiency of legal interpretation.1