AAI News Hub

#retrieval

17 briefs tagged #retrieval.

Research

Paper studies memory transfer across language models

The work tests frozen learned memories moved between model backbones using target-side reader adaptation.

arXiv cs.AI+1 outlet·10h ago
Tools

Sentence Transformers adds multi-vector retrieval support

Hugging Face details ColBERT-style late interaction in Sentence Transformers v6.0.

Hugging Face·1d ago
Research

Researchers push structured memory for AI agents

Six new papers propose schema, graph and skill-based systems for more reliable long-term agent memory.

arXiv cs.AI+1 outlet·6d ago
Research

Researchers target memory failures in long-term LLM agents

New papers propose graph, segment and interference methods for maintaining agent memory.

arXiv cs.AI+1 outlet·6d ago
Research

Researchers target reliability gaps in search agents

New papers propose evidence grounding, memory, training data and workflow methods for LLM agents.

arXiv cs.AI+1 outlet·Aug 12
Research

New papers target long-document VQA bottlenecks

InSight-doc, DocAtlas and DocMemo propose adaptive ways to find evidence across visually rich documents.

arXiv cs.LG+1 outlet·Aug 12
Research

Researchers propose ReMEMBER for dialogue summaries

The framework targets missing evidence in streaming dialogue summarization under fixed memory budgets.

arXiv cs.CL+1 outlet·Aug 11
Research

Researchers target visual evidence gaps in VLMs

New arXiv papers propose evidence selection, retrieval and token-pruning methods for multimodal QA.

arXiv cs.AI+1 outlet·Aug 7
Research

Researchers target credit assignment for search agents

RICE-PO and ABSeeker propose finer-grained training signals for retrieval and long-horizon search agents.

arXiv cs.CL+1 outlet·Aug 7
Research

LoT improves KB-VQA accuracy without model training

The framework highlights image regions and text evidence before answer generation.

arXiv cs.AI+1 outlet·Aug 7
Research

Researchers adapt Nemotron retrieval stack for Modern Greek

The work adds Greek retrieval training, reranking, grounded generation and a HERA benchmark.

arXiv cs.CL+1 outlet·Aug 6
Research

Researchers target credit assignment for search agents

New papers propose denser training signals for multi-step search, retrieval and reasoning agents.

arXiv cs.AI+1 outlet·Aug 6
Research

Benchmarks test whether LLM agents can improve skills

New papers evaluate skill learning, retrieval and memory in self-evolving LLM agents.

arXiv cs.CL+1 outlet·Aug 5
Research

Researchers flag ALiBi numerical failure in attention

The paper says floating-point underflow can make some ALiBi attention heads partially blind.

arXiv cs.CL+1 outlet·Aug 5
Research

Legal IR papers target leakage in case-law retrieval

New work proposes temporally fenced retrieval and a CJEU dataset for more realistic legal search evaluation.

arXiv cs.CL+1 outlet·Aug 4
Research

Researchers release UEmbed multimodal embeddings

UEmbed generates sparse lexical and dense representations in one decoder-only forward pass.

arXiv cs.AI+1 outlet·Aug 4
Research

New papers target long-horizon agent memory

Researchers propose harnesses and memory designs for agents that must work across extended tasks.

HF Daily Papers+1 outlet·Aug 4