AI Paper Atlas

Research map / Benchmarks / 2WikiMultiHopQA

2WikiMultiHopQA leaderboard

33 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on 2WikiMultiHopQA. Best EM: 72 (AgentTTS, NeurIPS 2025).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

2WikiMultiHopQA · EM

23 papers, each with its best reported number for its own method; higher is better.

#EM ↑MethodPaperTopic
172AgentTTS
GPT-o3-mini search agent
AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks
NeurIPS 2025 · Table: Comparison of search ti
Reasoning and chain of thought
269.6Interact-RAG
Qwen3-8B
Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrieval
ICLR 2026 · Table 1
Retrieval and knowledge
367INSES + Router
GLM-4
Beyond Explicit Edges: Robust Reasoning over Noisy and Sparse Knowledge Graphs
ICML 2026 · Table 2
Knowledge and temporal graphs
465.9Ours (Predictive)
Llama-3.1-8B
Predictive Prefetching for Retrieval-Augmented Generation
ICML 2026 · Table 2
Retrieval and knowledge
561.4CAM
GPT-4o-mini
CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension
NeurIPS 2025 · Table: Factual QA results
Retrieval and knowledge
660.2OPERA (MAPGRPO)
Qwen2.5-7B
OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval
AAAI 2026 · Table 1
Retrieval and knowledge
759.5QAFD-RAG
GPT-4o-mini
Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees
ICLR 2026 · Table 3
Knowledge and temporal graphs
858.6LiR3AG
Qwen3-8B (no-think) generator, GPT-4o-mini reranker/construc
LiR3AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation
AAAI 2026 · Table 1
Retrieval and knowledge
956.3RAG-R1-mq
Qwen2.5-7B-Instruct
RAG-R1:Incentivizing the Search and Reasoning Capabilities of LLMs Through Multi-Query Parallelism
AAAI 2026 · Table 3
Retrieval and knowledge
1055FREESON
Qwen2.5-7B
Retriever-Free Retrieval-Augmented Reasoning via Corpus-Traversing MCTS
NeurIPS 2026 · Table 1
Retrieval and knowledge
13 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

2WikiMultiHopQA · F1

17 papers, each with its best reported number for its own method; higher is better.

#F1 ↑MethodPaperTopic
176.8SCoRe-RL
Qwen2.5-7B-Instruct
Student-Centered Distillation Narrows the Agentic Gap Between Small and Large LLMs
ICML 2026 · Table 1
Agents, code and math
276.52InfoRE
GPT-4
Information Re-Organization Improves Reasoning in Large Language Models
NeurIPS 2024 · Table 2
Retrieval and knowledge
372.7OPERA (MAPGRPO)
Qwen2.5-7B
OPERA: A Reinforcement Learning--Enhanced Orchestrated Planner-Executor Architecture for Reasoning-Oriented Multi-Hop Retrieval
AAAI 2026 · Table 1
Retrieval and knowledge
472.4PANINI
GPT-4o-mini answer model
Panini: Continual Learning in Token Space via Structured Memory
ICML 2026 · Table 2
Retrieval and knowledge
570.2CAM
GPT-4o-mini
CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension
NeurIPS 2025 · Table: Factual QA results
Retrieval and knowledge
669.41QAFD-RAG
GPT-4o-mini
Query-Aware Flow Diffusion for Graph-Based RAG with Retrieval Guarantees
ICLR 2026 · Table 3
Knowledge and temporal graphs
768.2SiReRAG (GPT-3.5-Turbo)SiReRAG: Indexing Similar and Related Information for Multihop Reasoning
ICLR 2025 · QA performance table
Retrieval and knowledge
865.3LiR3AG
Qwen3-8B (no-think) generator, GPT-4o-mini reranker/construc
LiR3AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generation
AAAI 2026 · Table 1
Retrieval and knowledge
963FREESON
Qwen2.5-7B
Retriever-Free Retrieval-Augmented Reasoning via Corpus-Traversing MCTS
NeurIPS 2026 · Table 1
Retrieval and knowledge
1059.5HippoRAG (ColBERTv2)
ColBERTv2
HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
NeurIPS 2024 · QA performance table
Retrieval and knowledge
7 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.