HeadRank lifts preference optimization into attention space via entropy-regularized head selection and distribution regularizers to sharpen discriminability for efficient listwise reranking.
hub Mixed citations
Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Steps
Mixed citation behavior. Most common role is background (50%).
22
Pith papers citing it
Background
50% of classified citations
abstract
A multi-hop question answering (QA) dataset aims to test reasoning and inference skills by requiring a model to read multiple paragraphs to answer a given question. However, current datasets do not provide a complete explanation for the reasoning process from the question to the answer. Further, previous studies revealed that many examples in existing multi-hop datasets do not require multi-hop reasoning to answer a question. In this study, we present a new multi-hop QA dataset, called 2WikiMultiHopQA, which uses structured and unstructured data. In our dataset, we introduce the evidence information containing a reasoning path for multi-hop questions. The evidence information has two benefits: (i) providing a comprehensive explanation for predictions and (ii) evaluating the reasoning skills of a model. We carefully design a pipeline and a set of templates when generating a question-answer pair that guarantees the multi-hop steps and the quality of the questions. We also exploit the structured format in Wikidata and use logical rules to create questions that are natural but still require multi-hop reasoning. Through experiments, we demonstrate that our dataset is challenging for multi-hop models and it ensures that multi-hop reasoning is required.
hub tools
citation-role summary
background 4
dataset 3
method 1
citation-polarity summary
representative citing papers
Agentic search narrows the gap between dense RAG and GraphRAG but does not remove GraphRAG's advantage on complex multi-hop reasoning.
AtomicRAG replaces chunk-based and triple-based GraphRAG with atom-entity graphs that store facts as atomic units and use personalized PageRank plus relevance filtering to achieve higher retrieval accuracy and reasoning robustness on five benchmarks.
MemSearcher trains LLMs to manage compact memory in multi-turn searches via multi-context GRPO for end-to-end RL, outperforming ReAct-style baselines with stable token counts.
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
GiGPO adds a hierarchical grouping mechanism to group-based RL so that LLM agents receive both global trajectory and local step-level credit signals, yielding >12% gains on ALFWorld and >9% on WebShop over GRPO while keeping the same rollout and memory footprint.
MemGraphRAG uses a memory-based multi-agent system for globally consistent graph construction from fragmented corpora plus a memory-aware hierarchical retriever, claiming better benchmark performance than prior GraphRAG methods at similar cost.
LaProx reformulates KV cache eviction as an output-aware matrix approximation, enabling a unified global token selection strategy that preserves LLM performance at 5% cache size across long-context benchmarks.
EHRAG constructs structural hyperedges from sentence co-occurrence and semantic hyperedges from entity embedding clusters, then applies hybrid diffusion plus topic-aware PPR to retrieve top-k documents, outperforming baselines on four datasets with linear indexing cost and zero token overhead.
MemSearch-o1 mitigates memory dilution in agentic LLM search through reasoning-aligned token-level memory growth, retracing with a contribution function, and path reorganization, improving reasoning activation on benchmarks.
Tri-RAG turns external knowledge into Condition-Proof-Conclusion triplets and retrieves via the Condition anchor to improve efficiency and quality in LLM RAG.
MSA is an end-to-end trainable memory model using sparse attention and document-wise RoPE that scales to 100M tokens with linear complexity and less than 9% degradation.
MiroThinker shows that scaling agent-environment interactions via reinforcement learning lets a 72B open-source model reach up to 81.9% on GAIA and approach commercial performance on research benchmarks.
EvolveR enables LLM agents to self-evolve via a closed loop of distilling interaction trajectories into strategic principles offline and retrieving them to guide online decisions with policy reinforcement, yielding better results on multi-hop QA benchmarks.
A Multi-L KG and Quest-GNN with question-adaptive intra/inter-level message passing and synthesized pre-training data improves multi-hop RAG performance up to 33.8% on high-hop questions.
MoRE enables MLLMs to dynamically coordinate heterogeneous retrieval experts via Step-GRPO training, yielding over 7% average gains on open-domain QA benchmarks.
ZeroSearch uses supervised fine-tuning to create a simulated retrieval module and curriculum-based RL rollouts that degrade document quality to train LLMs on search capabilities without real search API calls.
ERL trains LLMs to erase faulty reasoning steps and regenerate them in place, yielding gains of up to 8.48% EM on multi-hop QA benchmarks like HotpotQA.
GRPO-SG is a sharpness-guided token-weighted variant of GRPO that downweights high-gradient tokens to stabilize optimization and improve generalization in reinforcement learning with verifiable rewards.
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.
citing papers explorer
-
Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems
Agentic search narrows the gap between dense RAG and GraphRAG but does not remove GraphRAG's advantage on complex multi-hop reasoning.
-
From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems
A survey that defines Compound AI Systems, proposes a multi-dimensional taxonomy based on component roles and orchestration strategies, reviews four foundational paradigms, and identifies key challenges for future research.
-
Reformulating KV Cache Eviction Problem for Long-Context LLM Inference
LaProx reformulates KV cache eviction as an output-aware matrix approximation, enabling a unified global token selection strategy that preserves LLM performance at 5% cache size across long-context benchmarks.
- OASES: Outcome-Aligned Search-Evaluation Co-Training for Agentic Search