NightFeats @ MMU-RAGent NeurIPS 2025: A Context-Optimized Multi-Agent RAG System for the Text-to-Text Track
Summary
NightFeats is a multi-agent RAG system that won Best Dynamic Evaluation at the MMU-RAGent competition at NeurIPS 2025. It uses a three-phase pipeline (retrieval, curation, composition) and outperforms proprietary baselines on human evaluations.
View Cached Full Text
Cached at: 06/11/26, 01:34 PM
# NightFeats @ MMU-RAGent NeurIPS 2025: A Context-Optimized Multi-Agent RAG System for the Text-to-Text Track Source: [https://arxiv.org/abs/2606.11199](https://arxiv.org/abs/2606.11199) [View PDF](https://arxiv.org/pdf/2606.11199) > Abstract: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\. ## Submission history From: Quentin Fever M \[[view email](https://arxiv.org/show-email/24901e67/2606.11199)\] **\[v1\]**Tue, 21 Apr 2026 19:18:07 UTC \(645 KB\)
Similar Articles
MCite-RL: Towards Reliable Multimodal RAG via Citation-enhanced Agentic Reinforcement Learning
MCite-RL is a citation-enhanced agentic reinforcement learning framework designed for reliable multimodal RAG, introducing iterative retrieval and reasoning for visual citations and a reward mechanism to jointly optimize answer accuracy and source traceability.
5ting at SemEval-2026 Task 8: Strong End-to-End Multi-Turn RAG via LLM-Based Reranking and Faithfulness Control
This paper presents 5ting, a system for multi-turn Retrieval-Augmented Generation (RAG) that combines BGE-M3 dense retrieval, FAISS indexing, LLM-based reranking, and evidence-constrained generation. The system achieves strong results on SemEval-2026 Task 8, with a retrieval nDCG@5 of 0.4719 and an end-to-end harmonic score of 0.5597.
Candidate-Constrained Retrieval-Augmented Generation for LongEval-RAG: System Design and Empirical Analysis
This paper presents a candidate-constrained RAG system for the LongEval-RAG task at CLEF 2026, combining deterministic provenance tracking with passage retrieval, query expansion, pseudo-relevance feedback, reciprocal rank fusion, evidence reranking, and citation-aware aggregation. An ablation study of ten pipeline variants shows that a rule-based chunking pipeline with sentence-level neural selection achieves the best performance.
@rohit4verse: Every night you're not running an autonomous research agent, you're hand-running experiments someone else automated mon…
Andrej Karpathy open-sourced an autonomous research agent that runs its own ML experiments overnight using a single GPU, automatically iterating on improvements by editing code and keeping changes that lower validation loss.
PhoenixNest-Video: Evidence-Grounded Multimodal Agent Framework for Automated Video Interview Assessment
PhoenixNest-Video introduces an evidence-grounded multimodal agent framework for automated video interview assessment, achieving 91.50% grade-level accuracy on a benchmark by using structured video graphs and reinforcement learning.