The paper introduces PersTurnBench, a novel benchmark and evaluator for assessing personalized user conversation satisfaction at specific turns, addressing the limitation of generic response quality m…

This paper proposes a multi-turn retrieval-augmented generation pipeline for conversational systems across four domains.

The paper introduces RHELM, a new benchmark designed to test LLMs' long-term memory by simulating realistic, complex, and evolving dialogues that integrate multiple heterogeneous data sources.

The study demonstrates that conditioning AI brand recommendations on a user's persona significantly alters the recommended product set, particularly for mid-market brands, and this effect is largest o…

RCEM is a novel conversational dense retrieval model that embeds query rewriting skills into the embedding model, significantly improving robust, context-aware search performance under distributional…

SPADER is a novel reinforcement learning framework that addresses the challenges of Multi-Answer Question Answering by improving credit assignment and promoting diverse exploration during long-horizon…

RASER introduces a family of cheap, router-based systems that selectively decide whether to perform expensive multi-hop retrieval, significantly reducing LLM token costs while maintaining state-of-the…

The paper introduces OCC-RAG, a family of compact, task-specialized Small Language Models (SLMs) designed to achieve highly faithful, multi-hop question answering grounded strictly in provided context…

The paper proposes MERIT, a dual-level, multi-horizon memory retrieval framework that significantly improves the performance of interactive text-to-SQL agents by providing both global and local memory…

Persona prompting does not universally improve LLM performance; instead, it systematically trades increased expertise depth for reduced clarity, making multi-metric evaluation essential.

DeSQ is a novel, KB-agnostic framework that improves Knowledge Base Question Answering by decomposing complex questions into atomic constraints and generating structured SPARQL queries, achieving supe…

CA-BED is a novel framework that improves LLM performance in interactive question-answering by integrating Bayesian Experimental Design to strategically select questions that maximize information gain…

SkillPager is a novel two-stage framework that efficiently selects minimal, execution-sufficient context from large procedural skill documents by leveraging typed semantic nodes, significantly reducin…

The paper introduces FRANZ, a communicative audit framework, to evaluate how LLMs frame responses to subjective questions, finding that LLMs exhibit statistically significant and coupled differences i…

The paper introduces Plan, a structured agentic behavior that decomposes multi-hop questions into ordered sub-questions before retrieval, and proposes a self-bootstrapping paradigm to train it without…

The paper introduces RefMem-Bench, a new benchmark for measuring reflective memory in long-horizon dialogue, and proposes REMIND, a framework that significantly improves models' ability to synthesize…

This paper proposes Tail-Aware Adaptive-k (TAA-k), a training-free framework for adaptive context selection in retrieval-augmented generation systems using Extreme Value Theory.

This paper investigates if team-based interaction improves LLM performance on complex reasoning tasks (ChGK), finding that structured team strategies significantly boost accuracy by acting as error-fi…

OmniRetrieval introduces a unified framework that handles natural language queries across diverse, heterogeneous knowledge sources (text, relational, graphs) by dispatching source-native queries witho…