Deep Research (DR) systems iteratively plan, retrieve evidence, and synthesize long-form reports in response to complex, open-ended queries. Existing approaches suffer from context overload, role entanglement, and error propagation over long horizons, while the most capable DR systems remain locked behind massive proprietary models. We present DeepDiver-DR (DD-DR), a multi-agent framework that decomposes the DR process into three specialized roles—planner, information seeker, and writer—coordinated through a persistent, file-based shared workspace. Each role is further equipped with fine-grained, DR-specific tools. To support rigorous evaluation, we introduce RubricWrite-Bench (RW-Bench), a benchmark of 100 rubric-based writing queries with a two-phase assessment of global report quality and point-level rubric fulfillment. Experiments show that DD-DR (30B) establishes a new state of the art among models at the same parameter scale on the DeepResearch Bench, and achieves performance competitive with leading proprietary DR systems on RW-Bench. Ablations further confirm the contribution of the architectural components.

Lifelong knowledge editing (LKE) aims to incrementally correct factual inaccuracies in large language models (LLMs), but sequential edits can lead to substantial degradation of capabilities. Existing approaches primarily rely on static parameter regularization, which restricts knowledge integration and fails to prevent cumulative capability degradation. We argue that an important source of this degradation lies in the temporal mismatch between locally editable factual knowledge and procedural knowledge, which is gradually acquired, guides task execution, and cannot be reliably updated by rapid edits. To this end, we formulate LKE as a dual-timescale process, explicitly decoupling fast-updating factual knowledge from slow-evolving procedural knowledge. Based on this formulation, we propose CaPEdit, a framework that preserves model capabilities under LKE. It first synthesizes procedural knowledge across successive edits, and subsequently performs parameter updates guided jointly by factual supervision and the synthesized procedural signal. To ensure stability under long edit sequences, CaPEdit is trained via a hybrid optimization scheme, combining step-wise updates for rapid factual correction with trajectory-level optimization to facilitate gradual procedural adaptation. Experiments demonstrate that CaPEdit improves capability preservation across all fundamental capabilities by 49.78%, achieves superior editing performance, and requires only 18.07% of the editing time of most existing methods.

Recent studies indicate a fundamental incompatibility between ID representations and language model (LM) representations, as they capture behavioral and semantic spaces respectively. This mismatch leads LM representations to consistently underperform ID representations in recommendation tasks. In this work, we revisit this problem and show, from an information-theoretic perspective, that LLM representations retain all discriminative information in ID representations. Based on this, we introduce a Profile-then-Embedding (PtE) framework for recommendation, consisting of a Profile Stage, in which semantic user and item profiles are generated jointly through LLM-based bidirectional reasoning over user-item interactions, and a Personalized Embedding Stage, which encodes these profiles into task-aligned recommendation embeddings. We demonstrate PtE’s effectiveness across three benchmark datasets, including cold-start and long-tail scenarios, achieving substantial gains in both discriminative and generative recommendation models.