arXiv AI
Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 7
Agentic Context Cracking: Token-Efficient Data Reasoning Agents via Adaptive Structuring of Unstructured Data
The paper introduces Agentic Context Cracking, a technique that adaptively and speculatively structures unstructured data during the reasoning process of large language model agents. By creating a sub-agent that extracts useful structure from documents as they are opened, the method reduces the need to repeatedly read large files, cutting token usage by 53% on the FanOutQA benchmark while maintaining accuracy. Over time, more queries are answered using the accumulated structured data, approaching the efficiency of a database lookup.
arXiv AI
Oct 16
Librarian Agents: Training LLMs to Curate Long-Context Workspaces that Anticipate Future Queries
The paper introduces Librarian Agents, a framework that trains large language models to proactively curate long-context workspaces by reorganizing raw documents into a hierarchical filesystem of synthetic files and reference links. This builder agent, optimized via reinforcement learning, aims to maximize downstream answering accuracy by anticipating future queries rather than reacting to them. Experiments show that Librarian Agents outperform leading retrieval and precomputation methods, achieving a 33‑point accuracy gain on BrowseComp‑Plus and a 31‑point improvement on BRIGHT in zero‑shot settings.
arXiv Computation and Language
Sep 10
Benchmarking Hybrid Deep Research Across Database Querying and Web Search
arXiv:2609.09410v1 Announce Type: new Abstract: While autonomous agents have made significant strides in "deep research" by iteratively navigating the open web to synthesize information, real-world p...
arXiv AI
Sep 25
Ingest-Time Fact Compilation for Cost-Efficient and Reliable Question Answering over Revised Corpora
The paper introduces ingest‑time fact compilation, an architecture that preprocesses and compiles corpus data into self‑contained facts with resolved revisions, deletions, and source trust. By storing this compiled state, query‑time models can retrieve answers directly, avoiding costly reconstruction from raw passages. Experiments show that this approach reduces read cost per question by 12.89× and token usage by 21.6× while maintaining accuracy.
arXiv AI
Sep 30
Follow the Entities: A Corpus Map for Agentic Search
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...
arXiv AI
Jun 6
A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable Reasoning
arXiv:2601. 21162v2 Announce Type: replace-cross Abstract: Graph Retrieval-Augmented Generation (Graph-RAG) enhances multihop question answering by organizing corpora into knowledge graphs and routing evidence through relational structure.