RECONTEXT is a recursive evidence replay technique that improves long-context reasoning in LLMs by constructing and replaying a query-conditioned evidence pool before final generation.
Title resolution pending
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
representative citing papers
Retrieving structured thinking traces as a corpus improves reasoning performance on AIME, LiveCodeBench, and GPQA over standard RAG or no retrieval.
MAGEO is a multi-agent system that distills validated editing patterns into reusable optimization skills for generative engines, outperforming heuristic baselines on visibility and fidelity via a new benchmark and evaluation protocol.
Code-switching creates a fundamental performance bottleneck for multilingual retrievers, causing drops of up to 27% on new benchmarks CSR-L and CS-MTEB, with embedding divergence as the key cause and vocabulary expansion insufficient to fix it.
A RAG method with a curated lexicon enables controlled Singlish generation from standard English through sparse substitutions, matching zero-shot prompting in perceived naturalness while achieving higher semantic preservation and edit minimality.
High OCR accuracy on standard metrics does not guarantee strong downstream RAG performance because structural and semantic errors cause retrieval and generation failures on challenging industrial documents.
Nomic AI produced and open-sourced a reproducible 8192-context English text embedder that exceeds OpenAI Ada-002 and text-embedding-3-small performance on MTEB short-context and LoCo long-context benchmarks.
FaithMed applies reinforcement learning with process-level rewards derived from evidence-based medicine rubrics to improve both task performance and reasoning faithfulness in medical LLMs.
MAGNET multi-agent generation with persona grounding and ATLAS graph verification yields 34-50% fewer hallucinations and annotations than single-model or IBSEN baselines at 100-page scale.
MINTEval benchmark shows current memory-augmented systems average 27.9% accuracy on long-horizon interference tasks, limited by retrieval and memory construction with degradation from intervening updates.
MASS-RAG uses distinct agents for evidence summarization, extraction, and reasoning, then synthesizes their outputs to improve answer quality over standard RAG baselines on four benchmarks, especially when evidence is distributed.
PaSaMaster, a recursive self-evolving agentic literature retrieval system, reports 16.5× higher F1 than Google Scholar and 37.8% higher F1 than GPT-5.2 on PaSaMaster-Bench across 38 disciplines with zero source hallucination at ~1% cost.
Proposes Modality-Aware Credit Assignment (MoCA) with blindfolded-reasoning proxy to reward perception fidelity separately from reasoning in VLMs.
citing papers explorer
-
ReContext: Recursive Evidence Replay as LLM Harness for Long-Context Reasoning
RECONTEXT is a recursive evidence replay technique that improves long-context reasoning in LLMs by constructing and replaying a query-conditioned evidence pool before final generation.
-
RAG over Thinking Traces Can Improve Reasoning Tasks
Retrieving structured thinking traces as a corpus improves reasoning performance on AIME, LiveCodeBench, and GPQA over standard RAG or no retrieval.
-
From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning
MAGEO is a multi-agent system that distills validated editing patterns into reusable optimization skills for generative engines, outperforming heuristic baselines on visibility and fidelity via a new benchmark and evaluation protocol.
-
Code-Switching Information Retrieval: Benchmarks, Analysis, and the Limits of Current Retrievers
Code-switching creates a fundamental performance bottleneck for multilingual retrievers, causing drops of up to 27% on new benchmarks CSR-L and CS-MTEB, with embedding divergence as the key cause and vocabulary expansion insufficient to fix it.
-
From Standard English to Singlish: A Retrieval-Augmented Approach for Code-Switched Creole Generation in Large Language Models
A RAG method with a curated lexicon enables controlled Singlish generation from standard English through sparse substitutions, matching zero-shot prompting in perceived naturalness while achieving higher semantic preservation and edit minimality.
-
When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation
High OCR accuracy on standard metrics does not guarantee strong downstream RAG performance because structural and semantic errors cause retrieval and generation failures on challenging industrial documents.
-
Nomic Embed: Training a Reproducible Long Context Text Embedder
Nomic AI produced and open-sourced a reproducible 8192-context English text embedder that exceeds OpenAI Ada-002 and text-embedding-3-small performance on MTEB short-context and LoCo long-context benchmarks.
-
FaithMed: Training LLMs For Faithful Evidence-Based Medical Reasoning
FaithMed applies reinforcement learning with process-level rewards derived from evidence-based medicine rubrics to improve both task performance and reasoning faithfulness in medical LLMs.
-
From Personas to Plot: Character-Grounded Multi-Agent Story Generation for Long-Form Narratives
MAGNET multi-agent generation with persona grounding and ATLAS graph verification yields 34-50% fewer hallucinations and annotations than single-model or IBSEN baselines at 100-page scale.
-
MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
MINTEval benchmark shows current memory-augmented systems average 27.9% accuracy on long-horizon interference tasks, limited by retrieval and memory construction with degradation from intervening updates.
-
MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation
MASS-RAG uses distinct agents for evidence summarization, extraction, and reasoning, then synthesizes their outputs to improve answer quality over standard RAG baselines on four benchmarks, especially when evidence is distributed.
-
Towards Recursive Self-Evolving Agentic Literature Retrieval
PaSaMaster, a recursive self-evolving agentic literature retrieval system, reports 16.5× higher F1 than Google Scholar and 37.8% higher F1 than GPT-5.2 on PaSaMaster-Bench across 38 disciplines with zero source hallucination at ~1% cost.
-
Bad Seeing or Bad Thinking? Rewarding Perception for Multimodal Reasoning
Proposes Modality-Aware Credit Assignment (MoCA) with blindfolded-reasoning proxy to reward perception fidelity separately from reasoning in VLMs.