HotpotQA

A new arXiv preprint (2608.19535v1) proposes telemetry-informed adaptive compression for retrieval-augmented generation (RAG) on edge devices, based on experiments on the NVIDIA Jetson AGX Thor with L…

Researchers propose IterCOMP, a training-free prompt compression framework that iteratively integrates evidence for multi-hop question answering, achieving substantial improvements in Exact Match and …

A new arXiv paper (2608.10694v1) proposes a cost-aware cross-tier transfer method for evolutionary optimization of LLM prompts and agentic programs, reducing search cost by 5.6-14x (up to 25-54x with …

A new paper on arXiv (2608.08237v1) proposes SAGE, a learned SLO-aware adaptive retrieval policy for production RAG systems that dynamically selects the number of passages per query. On Natural Questi…

A 2026 study by Daeyoung Roh and Donghee Han of 12,000 paired agent trajectories across HotpotQA, 2WikiMultiHopQA, and MuSiQue found that agentic RAG failures often stem from procedural errors: on MuS…

A study labeling 7,440 answers from four open-weight LLMs found that more than half of the hallucination labels were incorrect, and correcting them reordered the results. The author, Priyanshi Jain, r…

Researchers propose PI-Mem (Parallel-Iterative Memory), a mechanism that processes all chunks in parallel and iteratively refines a shared memory, enabling long-context reasoning up to 3.6 million tok…

Hubmesh, a new open-source project, introduces a local-first multi-hop retrieval system that combines Chroma vector search with an entity graph and Personalized PageRank, achieving 75.2% supporting-fa…

A new open-source library, hubmesh, adds a graph layer on top of Qdrant to answer multi-hop questions that stymie vector search. The library builds an entity-document graph at index time and uses Pers…

A new arXiv preprint (2608.00585v1) shows that per-chunk verification fails on multi-hop retrieval-augmented generation, with entailment scoring reaching only 0.643, 0.523, and 0.560 AUC on HotpotQA, …

A new family of graph theory-based defenses called TopoGuard, introduced by researchers in a preprint on arXiv, catches 21 times more split-knowledge attacks on Retrieval Augmented Generation (RAG) sy…

A developer built raven-retrieval, an open-source framework that benchmarks 19 retrieval pipelines on BEIR datasets with Bonferroni-corrected significance tests. The key finding is that top pipelines …

A new benchmark and training set called SelectBench, introduced by researchers in arXiv:2607.20090v1, shows that reinforcement learning via DAPO can modestly improve selective evidence adoption in ret…

Researchers at arXiv propose Contextual Information-Gain Policy Optimization (CIGPO) to fix a zero-advantage lock-in failure in outcome-only reinforcement learning for multi-turn evidence-reading agen…

A new approach using Quadratic Unconstrained Binary Optimization (QUBO) for evidence selection in retrieval-augmented generation (RAG) systems achieves competitive exact-match and token-F1 performance…

A new study on memory-managed long-context attention achieves a perfect 1.000 score on Track A, a controlled retrieval task, compared to a 0.333 baseline, and outperforms dense retrieval methods by up…

DeepSearch-Evolve introduces a self-distillation framework for training web agents in a controlled environment, achieving state-of-the-art results on benchmarks like BrowseComp, GAIA, and HotpotQA wit…

Researchers introduced DeepSearch-World, a deterministic and verifiable environment for training web agents, and DeepSearch-Evolve, a self-distillation framework that enables agents to improve from th…

AWS announced HippoRAG, a neurobiologically inspired retrieval augmented generation framework using Amazon Bedrock, Amazon Neptune, and Personalized PageRank to improve multi-hop reasoning in large la…

Researchers introduced Contrastive Reflection, an iterative prompt-optimization framework for agentic information retrieval workflows, which uses error-anchored behavioral slices and contrastive examp…