Optimist Deep Research is an open‑source agent that conducts literature research as an iterative, state‑centric process. It breaks a research question into a tree of subquestions, uses search intents to query multiple scholarly databases, and merges results into a provenance‑preserving document registry. The agent iteratively expands the registry via citation snowballing, evaluates evidence, and refines the research plan through a critic that can add, split, rephrase, deprioritize, or close subquestions, ultimately producing a report with every citation linked to a retrieved document.
arXiv:2609.23735v2 Announce Type: new Abstract: Scientific agents support a range of literature-based research tasks, such as retrieval, question answering, evidence-grounded generation, and claim as...
The paper introduces SPRA (Structured Paper Representation for Agents), a comprehensive representation of AI research papers that organizes key research elements—Problems, Contributions, Components, ExperimentSetups, Measures, and Findings—into typed relations for easier querying, traversal, and reuse. SPRA includes paper-level citation relations that capture dependencies, component usage, and comparisons, and it has been instantiated across more than one million AI papers, yielding millions of research units and internal relations. Empirical evaluations show that SPRA improves source-conditioned scientific QA and directed cross-paper reasoning over passage retrieval while significantly reducing input and output token counts, demonstrating its practicality for scientific workflows.
arXiv:2607. 28618v1 Announce Type: cross Abstract: Chemistry literature synthesis often requires assembling specific findings scattered across many publications, yet existing literature-search systems primarily return ranked document lists.
arXiv:2609.37226v1 Announce Type: cross Abstract: Answering questions and completing tasks over large document collections often requires connecting evidence spread across multiple documents, such as...
Agent Zero Memory is a provenance‑aware long‑term memory system for large language model agents that distills user interactions into three parallel memory structures: an episodic timeline, an associative entity‑event knowledge graph, and a semantic, citation‑locked hierarchical documentary memory. Retrieval is performed via an intent gate, source router, and concurrent searches across the three systems, producing integrated, cited answers that exclude fabrication and require evidence the reader has opened. The system achieves state‑of‑the‑art performance on LongMemEval (95.60%) and LoCoMo (93.60%) while offering a favorable accuracy‑cost‑latency trade‑off across multiple backbone LLMs.
JevGPT is a dual‑system architecture for autonomous research that combines fast evidence processing (System One) with deliberative research planning (System Two). System One quickly locates and evaluates relevant passages, while System Two sets evidence objectives and integrates findings into subsequent research steps. Experiments on question answering and document ranking demonstrate that JevGPT outperforms comparable agents, achieving faster completion, lower cost, and broader source coverage.
The paper introduces Incremental Open-Ended Deep Research (Incremental-OEDR), a new research setting that treats a report as an evolving state and updates it incrementally by preserving valid knowledge, revising outdated content, and incorporating new information. It proposes Structured Harness, which represents reports as structured outlines, sections, and evidence, enabling structured retrieval, a persistent evidence pool, and selective generation for efficient updates. A ten‑year temporal evaluation framework with Single‑Step and Long‑Chain tasks demonstrates that Incremental-OEDR maintains competitive report quality while improving continuity and reducing research costs, achieving up to 0.51 higher content‑level ROUGE‑L F1, 0.63 higher outline‑level EM F1, 33% lower token consumption, and 61% fewer search calls compared to traditional OEDR.
arXiv:2608. 14747v1 Announce Type: new Abstract: WANDR (Wide ANd Deep Research) is a benchmark of 500 realistic, challenging data-collection tasks for research agents.
The paper introduces Incremental Open-Ended Deep Research (Incremental-OEDR), a new research setting that treats a report as an evolving state and updates it incrementally by preserving valid knowledge, revising outdated content, and adding new information. It proposes Structured Harness, which represents reports as structured outlines, sections, and evidence, enabling structured retrieval, a persistent evidence pool, and selective generation for efficient updates. Experiments on DeepResearch Bench and DeepConsult show that Incremental-OEDR maintains competitive report quality while improving continuity, reducing token consumption by 33%, and cutting search calls by 61% compared to traditional OEDR.
arXiv:2610.15208v1 Announce Type: cross Abstract: Deep research requires connecting multiple steps of search, reasoning, and computation, with intermediate findings guiding what to investigate next....
Nomad is an autonomous system designed to explore and discover insights within large data corpora. It builds an explicit Exploration Map to systematically traverse a domain, generating and testing hypotheses with an explorer agent that leverages document, web, and database searches. After verification, it produces cited reports and meta-reports, and its evaluation framework assesses trustworthiness, quality, and diversity, showing superior performance over baselines on UN, WHO, and arXiv datasets.
arXiv:2608. 16185v1 Announce Type: cross Abstract: LLM agents increasingly answer questions over dynamic raw-document collections, where files may change before preprocessing, and relevant evidence (spans, sections, pages, or tables) is query-dependent.