Retrieval pipelines, vector search, chunking and reranking: how models are grounded in a corpus instead of their weights.
arXiv:2608. 20820v1 Announce Type: new Abstract: Large language models (LLMs) are vulnerable to multi-turn jailbreak attacks that progressively manipulate conversation context.
PrimeAgentOrchestrator (PAO) is a system that spawns new instances of Claude Code, Anthropic’s terminal-based coding agent, pre‑loaded with relevant memories from a user’s personal databases. PAO queries a PostgreSQL entity‑observation database and a Cloudflare Worker semantic search index in parallel, fuses the results, and injects the compiled briefing into the agent’s filesystem to exploit its auto‑read configuration. The paper reports four months of deployment, detailing three generations of context delivery mechanisms, the failure modes that prompted each redesign, and the engineering tradeoffs involved in integrating heterogeneous memory systems instead of building a unified one.
arXiv:2608.21208v1 Announce Type: cross Abstract: This paper investigates cross-agent specification portability using Oracle-to-PostgreSQL migration as a controlled software transformation task. The...
arXiv:2608.20909v1 Announce Type: new Abstract: Offline RL methods commonly jointly train the actor and critic, where the critic is used to guide the actor toward higher-value actions. This coupled l...
The paper introduces CoVR‑R, a reason‑aware composed video retrieval system that, given a reference video and an edit instruction, retrieves a target video that satisfies the edit. It employs a zero‑shot reason‑then‑retrieve pipeline using Qwen3.5‑27B to generate structured descriptions and dense embeddings for gallery videos, and performs edit reasoning on the query to produce a target‑video description used as the query embedding. The method combines dense retrieval with a TF‑IDF branch over generated texts, fusing the rankings with split‑specific weights, achieving state‑of‑the‑art retrieval metrics on both validation and blind test splits.
The paper introduces Trustworthy RAG, an evaluation agent designed to detect misinformation and knowledge poisoning in Retrieval-Augmented Generation systems. It combines natural language inference verification, a five-signal poison detector, and a weighted Trust Index to assess the reliability of retrieved content. Experiments on multiple LLMs show high accuracy and precision, with the agent effectively blocking unsafe advice in a secure-coding assistant scenario.
Granuscore is a reference‑free metric that measures the granularity of text by exploiting the structure of a hierarchical embedding space. It successfully reproduces known hierarchical orderings on the Granola‑EQ dataset, distinguishes granularity across different discourse contexts, and explains sentence‑specificity variations beyond sentence length. The authors also apply Granuscore to four question‑answering benchmarks, revealing systematic differences in granularity among questions, gold answers, and model outputs, thereby offering a new lens for assessing QA dataset difficulty.
arXiv:2608.15698v2 Announce Type: replace Abstract: Visual document retrieval is a critical component of multimodal retrieval-augmented generation, aiming to identify query-relevant pages from docume...
Joint-embedding predictive architectures (JEPAs) learn latent dynamics for planning and avoid representation collapse by matching features to maximum-entropy distributions such as isotropic Gaussians,...
The article discusses how Enterprise Document Intelligence should begin by parsing the folder structure rather than just PDFs, emphasizing that the index must reflect the case type’s requirements before any folder is accessed. It highlights that the two key questions to develop are not retrieval questions but rather focus on the relational tables needed for Retrieval-Augmented Generation (RAG) in a case file context.
The release of llm 0.33 introduces several key updates: it upgrades to the OpenAI Python library 3.x and switches the HTTP client from httpx to httpx2, adds comprehensive key handling for embedding functions, allows repeated template usage to combine configurations, and adds a reasoning_summary option for reasoning-capable responses. These changes improve compatibility, flexibility, and usability of the llm tool.
The article discusses a method for handling a folder of unrelated PDFs as a single long document with a nested outline. It highlights that without shared fields, an index cannot be built, so the approach uses one summary line per file and each file’s own table of contents, with retrieval routes extending down two levels. This structure enables retrieval-augmented generation (RAG) across multiple documents.
Causal discovery on topological event sequences is crucial for ensuring the reliability of networks. However, existing methods struggle to capture the complex causal relationships arising from concurr...
Enterprise Document Intelligence [Vol. 1 #7sexies] - The unit of retrieval doesn’t have to be a page or a paragraph.
arXiv:2508. 12682v2 Announce Type: replace Abstract: The global shift towards renewable energy presents unprecedented challenges for the electricity industry, making regulatory reasoning and compliance increasingly vital.
arXiv:2608. 20186v1 Announce Type: new Abstract: Non-invasive decoding of inner speech faces a fundamental data problem: a corpus pairing brain activity with a person's spontaneous inner monologue cannot be collected, and the available proxy paradigms (cued repetitive and retrospectively reported generative inner speech) are slow to acquire, poorly time-locked, and subject compliance is unverifiable.
arXiv:2608. 19652v1 Announce Type: new Abstract: As LLM-based agents are deployed for longer and higher-stakes tasks, their memory systems continue to have crucial gaps.
arXiv:2608. 19568v1 Announce Type: cross Abstract: Drafting a new Magic: The Gathering expansion begins before any pick from it has been observed: the complete card list is public, but the draft logs that supervised pick models train on do not yet exist.
arXiv:2606. 23487v2 Announce Type: replace Abstract: Medical vision-language models (VLMs) such as BiomedCLIP generalize broadly, but adapting them to a clinical service is as much a safety problem as an accuracy one.
arXiv:2603. 21875v2 Announce Type: replace-cross Abstract: Speech deepfake source verification systems aims to determine whether two synthetic speech utterances originate from the same source generator, often assuming that the resulting source embeddings are independent of speaker traits.