The article examines whether an apartment search agent can reduce the number of times it calls a predictive model while still identifying suitable matches. The author conducted 2,500 listing checks using Weights & Biases Weave, systematically eliminating unnecessary model computations, and evaluated each iteration against consistent reference answers.
arXiv:2608.22697v1 Announce Type: new Abstract: Search rankings are valuable because human attention is scarce and sequential. Higher-placed alternatives are easier to find, so they are examined and...
The article argues that well‑designed architecture can inadvertently eliminate signals that tooling relies on, turning a structural issue into a search problem. It highlights how drawing boundaries in systems can strip away essential cues needed by agents. The piece emphasizes the importance of considering signal preservation when designing architecture.
A minimal OpenAI Agents SDK implementation where retrieval becomes a search-read-decide loop The post Agentic RAG: Let the Agent Search appeared first on Towards Data Science .
arXiv:2509. 00761v4 Announce Type: replace Abstract: Large language models are increasingly deployed for legal question answering, where evaluations typically focus on multiple-choice accuracy.
The article explores the effects of removing a search box from an AI agent and instead providing it with typed tools, hard bounds, and a gate that it cannot bypass. It examines how the agent navigates a knowledge graph within strict limits and discusses findings from four models and one incorrect prediction regarding the value of this approach.
arXiv:2608.23045v1 Announce Type: new Abstract: Web search agents powered by Large Language Models (LLMs) show strong promise, but deep research tasks expose a recurring failure mode: once an agent h...
arXiv:2609.26086v1 Announce Type: new Abstract: An agentic retrieval system issues a sequence of search queries and must decide, at each step, whether the evidence collected so far is enough to stop....
The article "How Does a RAG Reranker Really Work?" explores the inner workings of Retrieval-Augmented Generation (RAG) rerankers, focusing on how data scientists explain the model’s operations behind the scenes. It discusses the impact of these insights on architecture decisions within enterprise document intelligence, specifically in the context of Enterprise Document Intelligence Vol.1 #2D. The piece highlights the importance of transparent model explanations for effective enterprise RAG implementation.
The study examines a two‑agent résumé screening process where both employer‑side and candidate‑side agents exchange evidence before deciding who advances, contrasting it with the traditional one‑call automated screening. Using GPT‑5.5 and Claude Opus 4.7 on 600 constructed résumé‑job pairs, the two‑agent method increased the proportion of applications advanced (up to 39.3% for GPT‑5.5) and raised pass rates for borderline cases from 4.5% to 26.2% (GPT‑5.5) and 6.5% to 16.1% (Opus 4.7). The results show that the screening procedure itself, rather than just the underlying model, determines which candidates reach human review and how consistently that access recurs.
arXiv:2608. 02751v2 Announce Type: replace-cross Abstract: Existing deep-research agents use a Search--Visit workflow that retrieves whole webpages without considering the structure they expose through titles, headings, sections, and metadata.
arXiv:2608.30303v1 Announce Type: new Abstract: Search agents reduce hallucination by grounding answers in retrieved web evidence. Yet reliance on retrieval also creates an attack surface: poisoned c...
The paper introduces Iris-mini and Iris-pro, two search agents trained at 35B and 397B parameter scales. They use a novel data pipeline that constructs reverse‑engineered multi‑hop queries from web hyperlinks, filters trajectories, and alternates supervised fine‑tuning with reinforcement learning in a process called SFT‑RL climbing. Evaluations on several benchmarks show that, with inference‑time context management, the agents achieve the best open‑source results in their parameter ranges.