FreeRet: MLLMs as Training-Free Retrievers
arXiv:2509.24621v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) are emerging as versatile foundations for mixed-modality retrieval. Yet, they often require heavy post-hoc
Knowledge catalogue
arXiv:2509.24621v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) are emerging as versatile foundations for mixed-modality retrieval. Yet, they often require heavy post-hoc
arXiv:2604.20860v1 Announce Type: cross Abstract: Despite the success of Retrieval-Augmented Generation (RAG) in grounding LLMs with external knowledge, its application over heterogeneous sources (e.g
Nice paper combining the strength of Skills and RAG. Most RAG systems retrieve on every query, whether the model needs help or not. This is wasteful when the model already knows the answer, and often
arXiv:2508.14323v3 Announce Type: replace Abstract: Tool-augmented LLMs invoke external functions to extend their capabilities, but errors in the invocation decision, such as calling a tool when none
arXiv:2608.29284v1 Announce Type: new Abstract: Deploying large language models for legal question answering raises challenges that general-purpose leaderboards do not capture, particularly for low-re
arXiv:2608.15956v1 Announce Type: new Abstract: Agentic retrieval workflows produce query, retrieval, and stopping traces as a byproduct of answering questions. We study how these traces can adapt a d
arXiv:2608.08809v1 Announce Type: new Abstract: A single model scale challenges the flexibility of a production retrieval system: some settings need it faster, others need a smaller index, and the rig
arXiv:2607.00606v1 Announce Type: new Abstract: Recent work on Thinking with Images makes vision a dynamic part of reasoning, but does so through generation: the model invokes external tools, synthesi
Most AI agents reset every session. @JenovaAIAgent's don't. Longest session on their platform: 16M tokens. All of it retrievable in <10ms via Pinecone vector retrieval. Result: Fast ramp to $1M+ ARR,
Databricks presents Instructed-Retriever-1, a system that achieves 3x faster search performance through parallel test-time scaling techniques. The approach optimizes retrieval operations by executing
arXiv:2605.18765v1 Announce Type: cross Abstract: To augment Large Language Models (LLMs) for multi-hop question answering, a mainstream solution within Graph Retrieval Augmented Generation (GraphRAG)
arXiv:2605.20104v1 Announce Type: cross Abstract: Speculative decoding (SD) accelerates large language model inference by leveraging a draft-then-verify paradigm. To maximize the acceptance rate, rece
arXiv:2605.18776v1 Announce Type: cross Abstract: The rapid spread of misinformation on social media highlights the need for robust, automated fact correction frameworks. However, existing works rely
arXiv:2610.21113v1 Announce Type: cross Abstract: Large-scale multi-agent ecosystems require mechanisms for discovering suitable agents without exposing entire registries to a large language model (LL
arXiv:2610.21318v1 Announce Type: cross Abstract: Multimodal document retrieval-augmented generation (RAG) has focused largely on retrieval, yet its answers depend on how well a vision-language model
arXiv:2609.37443v1 Announce Type: cross Abstract: Long-term memory enables language models to use past interactions in future conversations. However, evidence needed to answer a question may be scatte
arXiv:2609.37791v1 Announce Type: new Abstract: Every day, people continuously infer situational context and adjust the way they understand and remember the world. Context, signaled by the prefrontal
arXiv:2609.37345v1 Announce Type: new Abstract: Streaming video understanding requires Video Large Language Models (Video-LLMs) to reason over continuous visual streams under causal constraints. As th
Yann LeCun, Executive Chairman of AMI Labs, explains why LLMs are mostly retrieving human knowledge rather than thinking for themselves: LeCun starts with why so many people misread what these systems
arXiv:2609.14741v1 Announce Type: cross Abstract: Early thermal-mechanical lattice requirements are knowledge-intensive and often jointly unsatisfiable: an engineer asks for a cell that is light, stif
arXiv:2609.15830v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) can improve access to complex information; however, retrieving evidence alone does not ensure that answers are gr
Fine-tune your own embedding model for the price of a coffee. A great reranker can't surface a doc that was never retrieved. A RAG pipeline cannot cite a case it failed to retrieve. See how contrastiv
arXiv:2605.06235v2 Announce Type: replace-cross Abstract: Retrieval benchmarks are increasingly saturating, but we argue that efficient search is far from a solved problem. We identify a class of quer
arXiv:2604.14572v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) grounds LLM responses in external evidence but treats the model as a passive consumer of search results: it never
arXiv:2604.14616v1 Announce Type: new Abstract: Clinical value set authoring -- the task of identifying all codes in a standardized vocabulary that define a clinical concept -- is a recurring bottlene
arXiv:2609.19656v1 Announce Type: cross Abstract: Information retrieval is increasingly important as LLM agents tackle complex tasks involving diverse information needs. Because retrieval relies on an
arXiv:2609.12090v1 Announce Type: new Abstract: Video models increasingly use memory to preserve information over long sequences, with the assumption that gains come from retrieving and using the corr
arXiv:2607.17213v2 Announce Type: replace Abstract: Building long-horizon robot agents requires composing closed-loop pipelines -- perception, belief update, planning, and control -- whose components
arXiv:2609.11859v1 Announce Type: new Abstract: How does a language model's dependence on query-routing information and target knowledge change as it answers a question? We study this question through
arXiv:2609.03687v1 Announce Type: new Abstract: Coreference resolution is an important task in contextual reasoning. In this paper, we investigate the mechanism for representing and retrieving singula
arXiv:2609.01976v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly embedded in organizational work, yet their errors often pass human review. Prior research locates such f
arXiv:2608.27471v1 Announce Type: cross Abstract: Fallacies are arguments that employ invalid reasoning, making their automatic detection critical in sensitive contexts such as high-stakes political d
arXiv:2608.28568v1 Announce Type: new Abstract: Sign language production (SLP) aims to generate continuous signing motion from spoken language, often through gloss-to-pose generation. Prior work mainl
arXiv:2606.12451v2 Announce Type: replace-cross Abstract: Large language models deployed as agents over large tool catalogs face a critical tool-retrieval bottleneck. As embedding-based retrieval appr
arXiv:2608.26192v1 Announce Type: cross Abstract: How documents are segmented into retrievable chunks and how those chunks are embedded strongly affect Retrieval-Augmented Generation (RAG) quality, ye
arXiv:2608.25037v1 Announce Type: cross Abstract: Product linking, the entity-resolution task of mapping merchant product records to canonical catalog products, consolidates fragmented listings so dow
arXiv:2608.20810v1 Announce Type: cross Abstract: Multimodal information systems increasingly route generated visual content back through the same vision-language index that informed its production, s
arXiv:2608.13568v1 Announce Type: cross Abstract: Coding agents spend most of their context budget on retrieval. Lexical retrieval (grep) is universal, instant, and zero-setup, but noisy: it cannot te
arXiv:2608.06880v1 Announce Type: new Abstract: General-purpose skills promise reusable procedural knowledge for language agents, yet semantic relevance does not guarantee execution utility: a retriev
arXiv:2605.26778v1 Announce Type: new Abstract: Retrieval-augmented generation promises to ground language model outputs in external evidence, yet the field has no reliable way to verify whether retri
arXiv:2601.12369v3 Announce Type: replace Abstract: Deep Research Agents increasingly automate survey generation, yet whether they match human experts at retrieving essential papers and organizing the
arXiv:2604.22191v1 Announce Type: cross Abstract: In agentic workflows, LLMs frequently process retrieved contexts that are legally protected from further training. However, auditors currently lack a
arXiv:2601.07711v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems are usually defined by the combination of a generator and a retrieval component that extracts textual c
arXiv:2604.10721v1 Announce Type: cross Abstract: Natural-language Guided Cross-view Geo-localization (NGCG) aims to retrieve geo-tagged satellite imagery using textual descriptions of ground scenes.
Tool-augmented LLM agents discover relevant APIs from large registries before planning execution, yet finite context windows prohibit injecting all tool definitions into a single prompt. The dominant
arXiv:2606.15734v2 Announce Type: replace-cross Abstract: Continual post-training enables models to absorb emerging knowledge after deployment, but repeatedly updating shared parameters can accumulate
arXiv:2610.11727v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) has become a cornerstone in software engineering for enhancing Large Language Models (LLMs) with domain-specific
arXiv:2610.02202v1 Announce Type: new Abstract: What makes great scientists great? Even as AI systems start to make progress on open problems, scientists remain far ahead of them at sensing which prio
arXiv:2608.22695v1 Announce Type: cross Abstract: Agent ecosystems now include thousands of MATS components (Models, Agents, Tools, and Skills), yet their discovery still relies on in-context routing.
arXiv:2608.17484v1 Announce Type: new Abstract: Frozen vision-language-action (VLA) policies are increasingly improved at test time by sampling additional policy behaviors or introducing external demo
arXiv:2608.10528v1 Announce Type: cross Abstract: Anchor-based pointwise LLM reranking scores each candidate against a shared reference passage to recover cross-document context at pointwise cost. We
arXiv:2607.25276v1 Announce Type: new Abstract: We present FunnelAL, a retrieve-then-rank active learning system for single-class discovery, which adapts the multi-stage funnel architecture of industr
arXiv:2607.25182v1 Announce Type: cross Abstract: The ability to retrieve relevant tables for answering questions is a key task for structured information retrieval. Multi-stage retrieval systems rely
arXiv:2607.24097v1 Announce Type: new Abstract: Memory-augmented LLM agents typically answer queries by retrieving relevant memories and feeding them directly to an answer model. This retrieval-as-evi
Very cool idea to convert memory to skills. (bookmark it) Most agent memory systems retrieve past traces as passive context. MSCE turns them into executable skills instead. The training-free framework
arXiv:2607.05441v1 Announce Type: cross Abstract: Integrating external tools with Large Language Models (LLMs) has emerged as a promising paradigm for accomplishing complex tasks. Since LLMs still str
arXiv:2606.11680v1 Announce Type: new Abstract: Large language model (LLM) agents struggle with long-horizon tasks due to their inherent statelessness, requiring all task-relevant information to be en
arXiv:2605.27931v1 Announce Type: new Abstract: Scientific diagrams are essential for communicating complex methodologies in academic papers. A natural way for researchers to specify such diagrams is
arXiv:2605.25641v1 Announce Type: new Abstract: Agentic retrieval-augmented generation (RAG) systems in complex B2B (business-to-business) settings may often receive free-form response feedback. Rathe
arXiv:2605.06919v1 Announce Type: new Abstract: Large language models have demonstrated impressive retrieval-augmented capabilities. However, a crucial area remains underexplored: their ability to app