MetaSyn is a stage-level benchmark of 442 meta-analyses showing LLM agents retrieve up to 90.9% of eligible studies but include at most 52.7% in their final reports.
Dragin: Dynamic retrieval augmented generation based on the information needs of large language models
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 3
method 1
citation-polarity summary
representative citing papers
InlineCoder reframes repository-level code generation as function-level coding by using a draft anchor to inline the target function into its call graph for upstream usage and downstream dependency context.
SABER combines self-prior with multi-trace PK and CK reasoning representations to estimate reliability beliefs and drive trust-or-abstain decisions in knowledge-conflict RAG, improving accuracy over baselines.
Judge-R1 improves LLM judgment document generation by combining agentic legal information retrieval with GRPO-based rubric-guided optimization, outperforming baselines on the JuDGE benchmark.
Training LLMs to verbalize uncertainty explicitly at the end or during reasoning reduces overconfident errors and improves answer quality on factual tasks while enabling RAG triggers.
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.
DuMate-DeepResearch introduces a multi-agent deep research system with graph-based planning, recursive execution, and rubric optimization that reports new state-of-the-art scores of 58.03% and 61.95% on two benchmarks.
Unifying LLM long-context optimizations into a four-step memory pipeline and offloading sparse/irregular stages to FPGA yields up to 2.2× speedup and 4.7× energy savings versus GPU-only.
MODE-RAG introduces a VFE-driven multi-agent pipeline with MCTS and logit perturbations to lower hallucination and sycophancy rates in multimodal RAG, tested on the new ModeVent subset of MultiVent.
ECG foundation models for signal interpretation and medical LLMs for reasoning can be integrated into agentic systems for real-time cardiovascular intelligence on edge devices.
A survey that categorizes RAG methods for LLMs into four retrieval-centric stages, reviews their evolution and evaluation, and outlines challenges and future directions.
citing papers explorer
-
MetaSyn: A Benchmark for LLM Agents on Meta-Analysis Articles from Nature Portfolio
MetaSyn is a stage-level benchmark of 442 meta-analyses showing LLM agents retrieve up to 90.9% of eligible studies but include at most 52.7% in their final reports.
-
In Line with Context: Repository-Level Code Generation via Context Inlining
InlineCoder reframes repository-level code generation as function-level coding by using a draft anchor to inline the target function into its call graph for upstream usage and downstream dependency context.
-
Trust or Abstain? A Self-Aware RAG Approach
SABER combines self-prior with multi-trace PK and CK reasoning representations to estimate reliability beliefs and drive trust-or-abstain decisions in knowledge-conflict RAG, improving accuracy over baselines.
-
Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization
Judge-R1 improves LLM judgment document generation by combining agentic legal information retrieval with GRPO-based rubric-guided optimization, outperforming baselines on the JuDGE benchmark.
-
LLMs Should Express Uncertainty Explicitly
Training LLMs to verbalize uncertainty explicitly at the end or during reasoning reduces overconfident errors and improves answer quality on factual tasks while enabling RAG triggers.
-
Question-Adaptive Graph Learning for Multi-hop Retrieval Augmented Generation
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.
-
DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning
DuMate-DeepResearch introduces a multi-agent deep research system with graph-based planning, recursive execution, and rubric optimization that reports new state-of-the-art scores of 58.03% and 61.95% on two benchmarks.
-
Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference
Unifying LLM long-context optimizations into a four-step memory pipeline and offloading sparse/irregular stages to FPGA yields up to 2.2× speedup and 4.7× energy savings versus GPU-only.
-
MODE-RAG: Manifold Outlier Diagnosis and Energy-based Retrieval-Augmented Generation Evaluation
MODE-RAG introduces a VFE-driven multi-agent pipeline with MCTS and logit perturbations to lower hallucination and sycophancy rates in multimodal RAG, tested on the new ModeVent subset of MultiVent.
-
ECG Foundation Models and Medical LLMs for Agentic Cardiovascular Intelligence at the Edge: A Review and Outlook
ECG foundation models for signal interpretation and medical LLMs for reasoning can be integrated into agentic systems for real-time cardiovascular intelligence on edge devices.
-
A Survey on Retrieval-Augmented Text Generation for Large Language Models
A survey that categorizes RAG methods for LLMs into four retrieval-centric stages, reviews their evolution and evaluation, and outlines challenges and future directions.
- Adaptive Stopping for Multi-Turn LLM Reasoning