MemFlow routes queries by intent to tiered memory operations, nearly doubling accuracy of a 1.7B SLM on long-horizon benchmarks compared to full-context baselines.
hub Canonical reference
Raft: Adapting language model to domain specific rag
Canonical reference. 80% of citing Pith papers cite this work as background.
15
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 4
baseline 1
citation-polarity summary
representative citing papers
Chain of Evidence introduces a retriever-agnostic visual attribution method for iRAG that reasons over document screenshots with VLMs to output precise bounding boxes, outperforming text baselines on Wiki-CoE and SlideVQA.
MisEdu-RAG builds concept and instance hypergraphs for two-stage retrieval of pedagogical knowledge and student errors, improving feedback quality on the MisstepMath benchmark by 10.95% token-F1 and up to 15.3% on response dimensions.
Agentic search narrows the gap between dense RAG and GraphRAG but does not remove GraphRAG's advantage on complex multi-hop reasoning.
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.
CourseBlueprint builds a typed pipeline over a 23-lecture biomedical imaging corpus to generate prerequisite-aware, learner-adaptive videos with auditable engagement contracts and slide grounding.
Process supervision via RAG-Gym produces more reliable and generalizable search agents, with gains driven by higher-quality queries on out-of-domain multi-hop tasks.
Med-Gemini sets new records on 10 of 14 medical benchmarks including 91.1% on MedQA-USMLE, beats GPT-4V by 44.5% on multimodal tasks, and surpasses humans on medical text summarization.
CRAG improves RAG robustness via a retrieval quality evaluator that triggers web augmentation and a decompose-recompose filter to focus on relevant information, yielding better results on short- and long-form generation tasks.
ARMOR optimizes retrievers via joint RAG-likelihood and InfoNCE training with regularization toward the base encoder, yielding improved retrieval and QA on telecom benchmarks.
ChipLingo trains LLMs on EDA data via corpus construction, domain-adaptive pretraining, and RAG scenario alignment, reaching 59.7% accuracy with an 8B model and 70.02% with a 32B model on a new internal EDA benchmark.
Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.
HPC-LLM fine-tunes Llama 3.1 8B via QLoRA on 9k-24k HPC examples and adds dense retrieval to deliver practical support for job scheduling, MPI, and GPU workflows, approaching the performance of larger general models at lower memory and latency cost.
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.
citing papers explorer
-
MemFlow: Intent-Driven Memory Orchestration for Small Language Model Agents
MemFlow routes queries by intent to tiered memory operations, nearly doubling accuracy of a 1.7B SLM on long-horizon benchmarks compared to full-context baselines.
-
Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generation
Chain of Evidence introduces a retriever-agnostic visual attribution method for iRAG that reasons over document screenshots with VLMs to output precise bounding boxes, outperforming text baselines on Wiki-CoE and SlideVQA.
-
MisEdu-RAG: A Misconception-Aware Dual-Hypergraph RAG for Novice Math Teachers
MisEdu-RAG builds concept and instance hypergraphs for two-stage retrieval of pedagogical knowledge and student errors, improving feedback quality on the MisstepMath benchmark by 10.95% token-F1 and up to 15.3% on response dimensions.
-
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.
-
CourseBlueprint: A Structured Pipeline for Adaptive Pedagogical Video Generation Grounded in Course Corpora
CourseBlueprint builds a typed pipeline over a 23-lecture biomedical imaging corpus to generate prerequisite-aware, learner-adaptive videos with auditable engagement contracts and slide grounding.
-
Supervising the search process produces reliable and generalizable information-seeking agents
Process supervision via RAG-Gym produces more reliable and generalizable search agents, with gains driven by higher-quality queries on out-of-domain multi-hop tasks.
-
Capabilities of Gemini Models in Medicine
Med-Gemini sets new records on 10 of 14 medical benchmarks including 91.1% on MedQA-USMLE, beats GPT-4V by 44.5% on multimodal tasks, and surpasses humans on medical text summarization.
-
Corrective Retrieval Augmented Generation
CRAG improves RAG robustness via a retrieval quality evaluator that triggers web augmentation and a decompose-recompose filter to focus on relevant information, yielding better results on short- and long-form generation tasks.
-
ARMOR: Adaptive Retriever Optimization for Low-Resource Telecom Question Answering
ARMOR optimizes retrievers via joint RAG-likelihood and InfoNCE training with regularization toward the base encoder, yielding improved retrieval and QA on telecom benchmarks.
-
ChipLingo: A Systematic Training Framework for Large Language Models in EDA
ChipLingo trains LLMs on EDA data via corpus construction, domain-adaptive pretraining, and RAG scenario alignment, reaching 59.7% accuracy with an 8B model and 70.02% with a 32B model on a new internal EDA benchmark.
-
Advancing Multi-Agent RAG Systems with Minimalist Reinforcement Learning
Mujica-MyGo decomposes multi-turn RAG interactions via multi-agent workflows and applies minimalist policy gradient optimization to improve performance on QA benchmarks while avoiding long-context problems.
-
HPC-LLM: Practical Domain Adaptation and Retrieval-Augmented Generation for HPC Support
HPC-LLM fine-tunes Llama 3.1 8B via QLoRA on 9k-24k HPC examples and adds dense retrieval to deliver practical support for job scheduling, MPI, and GPU workflows, approaching the performance of larger general models at lower memory and latency cost.
-
Agentic Reasoning for Large Language Models
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.
-
Retrieval-Augmented Generation for Large Language Models: A Survey
A survey of RAG paradigms, components, benchmarks, and challenges for improving LLMs on knowledge-intensive tasks.