UNREAL: Unifying Retrieval and Long-Context with a Single Model

UNREAL unifies retrieval and long-context evidence selection via frozen LLM representations with minimal parameters, outperforming state-of-the-art retrievers and improving long-context accuracy substantially.

Edan Kinderman, Elad Hoffer, Yochai Blau, Brian Chmiel and 3 more

Published Oct 6, 2026 · ▲ 15 on Hugging Face

AGO AI Quality Gate: Evidence-First Release Decisions for Retrieval-Augmented Generation

AGO is an evidence-first quality gate for RAG that treats judge errors and missing data as explicit outcomes, using stratified beta-binomial gates and mandatory meta-evaluation to reduce unsafe promotion to 22.2%-35.1% versus 29.3%-41.8% for naive gates.

Giulio Zeloni, Enrico Lo Conte, Salvatore Rionero, Giuseppe Santoro and 2 more

Published Oct 1, 2026 · 0 citations · ▲ 13 on Hugging Face

Where Does Retrieval-Based Open-Ended Evaluation Fail? Automatic Taxonomy Induction from Long-Form Medical Answer Factuality Verification

Automatic taxonomies reveal retrieval and verifier reasoning failures persist across scaled medical retrieve-then-verify systems, showing fundamental open-ended evaluation limits.

Heyuan Huang, Jirui Dai, Alexandra DeLucia, Sonal Joshi and 4 more

Published Sep 24, 2026 · 0 citations · ▲ 12 on Hugging Face

CoRAG: Enhancing Hybrid Retrieval-Augmented Generation through a Cooperative Retriever Architecture

CoRAG dynamically selects textual or graph retrieval and blends results for global hybrid knowledge access, outperforming local hybrid RAG on QA benchmarks.

Zaiyi Zheng, Song Wang, Zihan Chen, Yaochen Zhu and 4 more

Published 2025 · 0 citations

How Much Evidence Should Retrieval-Augmented In-Context Learning Use Under Distribution Shift?

Chen Wang

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Machine Learning-Driven RAG System Design

Anastasia Orlova, Nina Gubina, Aleksei Dmitrenko, Arsen Sarkisyan and 6 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

LP-RAG: Learning to Retrieve with Link Predictors

Erik Jhones Freitas do Nascimento, Jorge Franco, Amauri Souza

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

When Does Graph Retrieval Become Answer-Supporting Evidence? A Diagnostic Audit of GraphRAG

Chenghua Duan, Zhuo Wang, boheng liu, Ziyu Li and 4 more

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

LEAP: Library-driven Evolutionary Abstraction Paradigm for Large Language Models

Fanbin Lu, Chi-Wing Fu, Jiaya Jia

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

SAGE: Semantic Ambiguity Guided Capacity Expansion for Retrieval-Augmented Generation

Xunlei Chen, Jinyu Guo, Yi Gong, Qirui Ye and 3 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Geometric Gain Graph: Zero-Token Graph Construction for Multi-Hop RAG

Zeliang Li, Xiaofen Xing, Wenyu Tao, Kailing Guo and 1 more

Sydney Poster Session 3, Wed, Dec 9, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

TRIM: A Theory of Retrieval with Incremental Memory -- Defect, Benefit, and Critical Horizon

Hiroyuki Kasai

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026

ShiftRAG: Bypassing the Textual Bottleneck via Decoupled Learning and Continuous Soft Tokens

Youmin Ko, Jihong Jeong, Hyunjoon Kim

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

RealDev-QA: Trajectory-Level Diagnosis for Developer RAG Under Real-World Noises

Tianling Lan, Yao Junxiao, Tingyang Chen, Cibo Yu and 4 more

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Not All Gap Correction Helps: A Geometric View of External Information in LLM Inference

Dingzirui Wang, Xuanliang Zhang, Keyan Xu, Qingfu Zhu and 2 more

Paris Poster Session 2, Wed, Dec 9, 5:00 PM–7:00 PM, Paris Poster Hall · Published 2026

Constraint Retrieval Is Not Constraint Enforcement in Large Language Models

Yongkang Yang, Xiankun Lin, Lixin Liu, Ziyan Liu and 4 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

Do LLMs Bind Episodes? Probing Cross-Episode Parametric Retrieval Through Shared Cues

Francesco Mantovani, Alberto Eusebio, Alexis Huet, Giulio Franzese and 3 more

Paris Poster Session 3, Thu, Dec 10, 12:30 PM–2:30 PM, Paris Poster Hall · Published 2026

TRIDENT: Post-Selection Evidence Accountability for Token-Efficient RAG

Wutong Zhang, Jiong Lou, Richard Liu, Sizhe Zhang and 5 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

OpticalRAG: Pixel-Space Compression for Token-Efficient Retrieval-Augmented Generation

Senhao Liu, Yuheng Zhang, Chunyu Wei, Yueguo Chen and 1 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

InduceKV: Fixed-Footprint Continual Adaptation of Multimodal LLMs via Inducing KV Memories

InduceKV stores attention-ready KV memory entries with fixed memory budgets to adapt multimodal LLMs continually, outperforming PEFT, replay, and prompt-retrieval baselines.

Qianyu Chen, Ziteng Feng, Canran Xiao, Runxuan Tang

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

SLIDERS: Systematic Reviews via Automated Evidence Synthesis and Reconciliation

SLIDERS automates systematic reviews via LLM-based evidence extraction and reconciliation, achieving near 90% accuracy over multi-million-token corpora and answering 58-78% of follow-up questions correctly.

Harshit Joshi, Priyank Shethia, Jadelynn Dao, Monica Lam

Sydney Poster Session 6, Thu, Dec 10, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 16 on Hugging Face · Code ★ 31

In-Context Optimization for Retrieval-Augmented Generation: A Gradient-Descent Perspective

Retrieval-augmented generation is framed as in-context optimization via linear self-attention gradient descent, yielding a frozen-model forward-only interface update that improves QA with low per-query cost.

mingchen li, Jiatan Huang, Chuxu Zhang, Liang Zhao and 1 more

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

Beyond Raw Context Transfer: Representation-based Federated Retrieval-Augmented Generation

FedRepRAG is a federated RAG framework that exchanges only compact latent representations across clients to reduce inference overhead, outperforming local retrieval baselines on decentralized VQA and QA tasks.

Can Peng, Yu Liu, Yingyu Yang, Anjie Le and 3 more

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

LogicTree-RAG: Logic Tree-guided Retrieval-Augmented Generation for Long-form Patent Drafting

LogicTree-RAG induces hierarchical logic trees to organize long-form patent drafting, improving content quality and token efficiency without expert outlines.

Jiaqi Zhu, Naili Xing, Pan Hexiang, Haotian Gao and 3 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

Memory Retrieval for Changing Preferences

A Bayes-factor utility framework selects memory turns by evidence of latent preference changes and regulates access accordingly. It outperforms embedding retrieval on preference-intensive long-context dialogue tasks.

Yuehan Qin, Li Li, Linxin Song, Jiate Li and 3 more

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

Latent Abstraction for Retrieval-Augmented Generation

LAnR unifies RAG by using a single LLM's latent space for dense retrieval and adaptive stopping, outperforming existing methods with fewer retrieval calls.

Thi Ha Lan Nguyen, Nguyen Minh-Anh, Dung Le

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

Frozen Memory Is Not Enough: Rethinking External Memory as Extraction

Cross-model frozen-memory extraction shows target-aligned readers matter more than frozen tables, with dual-layer readers nearly closing reuse gaps and compatible interfaces enabling direct utility.

Mingyuan Li, Guangsheng Yu, Xu Wang, Shaoxiong Ji

Sydney Poster Session 2, Tue, Dec 8, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026 · ▲ 8 on Hugging Face · Code ★ 3

Retrieval from Within: An Intrinsic Capability of Attention-Based Models

INTRA unifies retrieval and generation via decoder attention over internal encoder states, outperforming engineered RAG on question-answering benchmarks.

Elad Hoffer, Yochai Blau, Edan kinderman, Ron Banner and 2 more

Paris Poster Session 4, Thu, Dec 10, 5:30 PM–7:30 PM, Paris Poster Hall · Published 2026 · ▲ 10 on Hugging Face