mlsanityData to 14 Oct 2026

NightFeats @ MMU-RAGent NeurIPS 2025: A Context-Optimized Multi-Agent RAG System for the Text-to-Text Track

arXiv 2606.11199 ↗First posted 21 Apr 2026cs.CL cs.AI cs.IRcited by 0

On the map: Retrieval-augmented generation → Agentic RAG, agents and memory

also in 1 more
Abstract (arXiv)

We present NightFeats, a structured multi-agent retrieval-augmented generation (RAG) system submitted to the MMU-RAGent competition at NeurIPS 2025, where it was awarded Best Dynamic Evaluation in the text-to-text track. Rather than targeting benchmark maximization, this work proposes a principled pipeline that decomposes knowledge synthesis into three coordinated phases: retrieval, curation, and composition, each governed by explicit intermediate representations and handoff contracts. Inspired by Agentic Context Engineering (ACE), the system introduces temporal-semantic reranking, bounded contradiction reconciliation, and citation-preserving composition as core architectural primitives. Competition results show that NightFeats surpasses proprietary baselines including Claude-SonnetV2 and Nova-Pro on LLM-as-a-Judge and Human Likert evaluations, confirming that architectural transparency and verifiable evidence grounding are better aligned with human preferences than systems optimizing narrowly for automatic similarity metrics.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agentic RAG, agents and memory, one of 15 directions in Retrieval-augmented generation. Builds on 3 of its 3 references that are in the map. First posted on arXiv 21 Apr 2026.

Builds on

3 of 3 references.

References · 3

  1. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  3. 2025RAG Meets Temporal Graphs: Time-Sensitive Modeling and Retrieval for Evolving Knowledgecited by 13

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG
  2. 2026Q2D-Web: A Large-Scale Benchmark for Retrieval in Agentic RAG Systems
  3. 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces
  4. 2026Agent-Orchestrated Adaptive RAG: A Comparative Study on Structured and Multi-Hop Retrieval
  5. 2025HM-RAG: Hierarchical Multi-Agent Multimodal Retrieval Augmented Generation
  6. 2025RAGCap-Bench: Benchmarking Capabilities of LLMs in Agentic Retrieval Augmented Generation Systems
  7. 2025BRIGHT+: Upgrading the BRIGHT Benchmark with MARCUS, a Multi-Agent RAG Clean-Up Suite
  8. 2026MemGraphRAG: Memory-based Multi-Agent System for Graph Retrieval-Augmented Generation