Maven is an RL method using answer-conditioned evidence-state values to assign rewards to add, link, and drop actions on evidence memory, outperforming outcome-only baselines on LongBench v2, LongReason, and RULER.
hub
Longrag: Enhancing retrieval-augmented generation with long-context llms
15 Pith papers cite this work. Polarity classification is still indexing.
15
Pith papers citing it
hub tools
citation-role summary
background 1
method 1
citation-polarity summary
representative citing papers
MemLens benchmark shows long-context LVLMs lose accuracy with length while memory agents lose visual fidelity, with multi-session reasoning below 30% for most systems and neither approach solving the task alone.
IntrAgent uses a two-stage pipeline of section ranking and iterative reading to perform content-grounded literature information retrieval, achieving 13.2% higher accuracy than RAG and agent baselines on the new IntraBench benchmark.
UMG-RAG improves long-document RAG by uncertainty-aware fusion of multi-granularity retrievals from complementary dense and sparse retrievers, plus a parent-promotion variant.
HMARS introduces a hierarchical multi-agent memory system that outperforms standard retrieval and other baselines on long-document and multi-turn reasoning tasks through improved evidence coverage.
HAGE proposes a trainable weighted graph memory framework with LLM intent classification, dynamic edge modulation, and RL optimization that improves long-horizon reasoning accuracy in agentic LLMs over static baselines.
SAGE is a training-free context reduction method that converts attention signals from a small LLM into a differential relevance heatmap to select top units for downstream QA, achieving competitive accuracy at 10% token budget on benchmarks like QuALITY-hard.
A hybrid graph-text retrieval system for cyber threat intelligence improves multi-hop question answering by up to 35% over vector-based RAG on a 3,300-question benchmark.
DualView fuses local cross-attention and global context aggregation via adaptive gating to rerank fixed candidate sets for multi-hop QA, reporting 99.4% Top-4 Recall on MuSiQue at 4 ms latency while beating larger cross-encoders.
EviOmni unifies evidence reasoning and extraction in a single RL trajectory with token masking and verifiable rewards for answer, length, and format to produce compact high-quality evidence for RAG.
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.
Enforcing sentence-level citations degrades LLM attribution quality by 16-276% versus paragraph-level, with larger models penalized more due to disrupted semantic synthesis.
Hybrid Document-Routed Retrieval (HDRR) filters financial filings with LLM document routing then scopes chunk retrieval, beating pure chunk and pure file routing on FinDER accuracy and efficiency.
Experience-RAG Skill is a reusable agent skill that selects retrieval strategies via experience memory, achieving 0.8924 nDCG@10 on BeIR/nq, hotpotqa, and scifact while outperforming fixed retriever baselines.
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.
citing papers explorer
-
Evidence-State Rewards for Long-Context Reasoning
Maven is an RL method using answer-conditioned evidence-state values to assign rewards to add, link, and drop actions on evidence memory, outperforming outcome-only baselines on LongBench v2, LongReason, and RULER.
-
MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models
MemLens benchmark shows long-context LVLMs lose accuracy with length while memory agents lose visual fidelity, with multi-session reasoning below 30% for most systems and neither approach solving the task alone.
-
IntrAgent: An LLM Agent for Content-Grounded Information Retrieval through Literature Review
IntrAgent uses a two-stage pipeline of section ranking and iterative reading to perform content-grounded literature information retrieval, achieving 13.2% higher accuracy than RAG and agent baselines on the new IntraBench benchmark.
-
Uncertainty-Aware Hybrid Retrieval for Long-Document RAG
UMG-RAG improves long-document RAG by uncertainty-aware fusion of multi-granularity retrievals from complementary dense and sparse retrievers, plus a parent-promotion variant.
-
HMARS: A Hierarchical Multi-Agent Memory System for Long-Context Reasoning
HMARS introduces a hierarchical multi-agent memory system that outperforms standard retrieval and other baselines on long-document and multi-turn reasoning tasks through improved evidence coverage.
-
HAGE: Harnessing Agentic Memory via RL-Driven Weighted Graph Evolution
HAGE proposes a trainable weighted graph memory framework with LLM intent classification, dynamic edge modulation, and RL optimization that improves long-horizon reasoning accuracy in agentic LLMs over static baselines.
-
SAGE: Selective Attention-Guided Extraction for Token-Efficient Document Indexing
SAGE is a training-free context reduction method that converts attention signals from a small LLM into a differential relevance heatmap to select top units for downstream QA, achieving competitive accuracy at 10% token budget on benchmarks like QuALITY-hard.
-
Beyond RAG for Cyber Threat Intelligence: A Systematic Evaluation of Graph-Based and Agentic Retrieval
A hybrid graph-text retrieval system for cyber threat intelligence improves multi-hop question answering by up to 35% over vector-based RAG on a 3,300-question benchmark.
-
DualView: Adaptive Local-Global Fusion for Multi-Hop Document Reranking
DualView fuses local cross-attention and global context aggregation via adaptive gating to rerank fixed candidate sets for multi-hop QA, reporting 99.4% Top-4 Recall on MuSiQue at 4 ms latency while beating larger cross-encoders.
-
Learning to Extract Rational Evidence via Reinforcement Learning for Retrieval-Augmented Generation
EviOmni unifies evidence reasoning and extraction in a single RL trajectory with token masking and verifiable rewards for answer, length, and format to produce compact high-quality evidence for RAG.
-
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.
-
Are Finer Citations Always Better? Rethinking Granularity for Attributed Generation
Enforcing sentence-level citations degrades LLM attribution quality by 16-276% versus paragraph-level, with larger models penalized more due to disrupted semantic synthesis.
-
Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off
Hybrid Document-Routed Retrieval (HDRR) filters financial filings with LLM document routing then scopes chunk retrieval, beating pure chunk and pure file routing on FinDER accuracy and efficiency.
-
An Agent-Oriented Pluggable Experience-RAG Skill for Experience-Driven Retrieval Strategy Orchestration
Experience-RAG Skill is a reusable agent skill that selects retrieval strategies via experience memory, achieving 0.8924 nDCG@10 on BeIR/nq, hotpotqa, and scifact while outperforming fixed retriever baselines.
-
A Survey of Scaling in Large Language Model Reasoning
A survey categorizing scaling in LLM reasoning across input size, steps, rounds, training, and future directions, noting that scaling can negatively affect performance.