IterCOMP: Reasoning-aware Adaptive Prompt Compression for Multi-hop Question Answering

MEGRAG: Multi-Granular Evidence Graphs for Answer-Aware Multi-Hop RAG

MEGRAG is an answer-aware framework that represents multi-hop reasoning as a path-structured multi-granular evidence graph and uses the resulting intermediate answer and prior reasoning to decide whether the Initial Query has been resolved.

QUBO-Optimized Evidence Selection for Retrieval-Augmented Question Answering with Unconventional Solvers

The QUBO selector achieves competitive exact-match and token-F1 performance relative to LLM-based selectors while providing a solver-compatible formulation for structured evidence selection, suggesting that multi-hop evidence selection can be cast as discrete optimization, opening a path toward RAG pipelines where LLMs are reserved for semantic processing and answer generation, while context selection is handled by Ising/QUBO-compatible solvers.

MCoRe: Multi-Entry Complementary Retrieval with Reflection-Guided Iteration for Multi-Hop QA

MCoRe, a multi-entry complementary retrieval framework with reflection-guided iteration for multi-hop QA that enables multi-entry complementary retrieval by indexing entry units at multiple semantic resolutions with explicit links to chunk evidence, and fusing cross-resolution hits via chunk-level voting to form a compact evidence set for answer generation.

Stop Thinking, Start Looking: Efficient Post-Training for Multimodal Document Question Answering via Reasoning-Free Alignment

Perception-RFT is introduced, a training framework that applies Group Relative Policy Optimization (GRPO) to multimodal document QA, bypassing intermediate reasoning tokens to directly align visual features with structured grounding outputs, and a reasoning variant under identical reward settings is constructed.

Efficient and reliable multimodal retrieval-augmented question answering via greedy leave-one-out consistency pruning

DocHop: Benchmarking Out-of-domain Multi-hop Reasoning in Information-Dense Documents

Multimodal Large Language Models (MLLMs) have achieved strong performance on structured visual understanding tasks such as chart and document question answering. However, existing benchmarks typically evaluate these domains in isolation, leaving underexplored a key capability: whether models can use textual context to determine how chart evidence should be selected, interpreted, and aggregated. We introduce DocHop, a benchmark for integrated chart--context reasoning in document-style images. In DocHop, the document narrative specifies multi-step compositional constraints, while charts provide the corresponding data values. Questions are grounded on a semantic reference label defined in the narrative, requiring models to resolve target entities from context before aggregating evidence across multiple charts. To enable systematic evaluation, we construct DocHop via a stochastic logic-first generation pipeline with controllable reasoning depth and visual density, covering 2,074 examples across six task categories. Experiments on a wide range of proprietary and open-source MLLMs show a substantial gap to human performance: annotators achieve over 90% accuracy, while the best model reaches only 62.83%. Reasoning-enhanced models consistently show improved results, but performance degrades as reasoning complexity increases. Overall, DocHop provides a controlled testbed for challenging multi-hop document reasoning.