·
DataBubble
  • Home
  • Models
  • News
  • Compare
  • Boards
  • Pricing
  • About
  • Newsletter
  • Methodology
  • Contact
Latest
Tradeoff-Aware Territory Design: A Multi-Objective Decision System for Enterprise Customer-to-Seller Allocation19m◆Phronix: The Capability-Centric Learning Paradigm for Agents19m◆Patronizing and Condescending Language Detection in English and Mandarin19m◆PaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean19m◆Don't Forget What You Just Learned: Self-Directed Repair Turns Agent Mistakes Into Lasting Lessons19m◆TACS-RF: Tool-driven Agentic Circuit Synthesis of RF and mmWave Modules19m◆Permission to Retry: A Study of Authorization and Recovery in AI Agent Workflows19m◆Beyond On-Policy vs. Off-Policy: At What Level Should LLM Agent Distillation Follow the Student?19m◆$M^3$: A Multi-LLM System for Multi-Turn Jailbreaking as a Markov Decision Process19m◆Knowing Whom to Trust is not Enough: The Trust--Agreement Gap in Repeated Multi-Party LLM Negotiation19m◆Reproducible Evaluation as the Substrate for Safe Prompt Compression in Production Agents19m◆The Helpful Agent Problem: When Emergent Cooperation Among LLM Agents Bypasses Intended Workflows19m◆CEMIR vs. FISER: a comparative study of reasoning-based and enrichment-based approaches to pragmatic intent recognition19m◆BARC-Bench: Benign Asks, Risky Consequences19m◆RSI-Opt: Recursive Self-Improvement Optimizer Agents For Model Training19m◆PPO vs. SAC: A Comparative Study for Cooperative Motion Control of Dual-Arm Space Robots19m◆Do AI-for-Science Agents Preserve Model Safety?19m◆Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?19m◆HyScale: Scaling Long-Context Training for Learned Sparse Attention19m◆Understanding Communication Failures in Multi-Agent LLM Systems19m◆Tradeoff-Aware Territory Design: A Multi-Objective Decision System for Enterprise Customer-to-Seller Allocation19m◆Phronix: The Capability-Centric Learning Paradigm for Agents19m◆Patronizing and Condescending Language Detection in English and Mandarin19m◆PaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean19m◆Don't Forget What You Just Learned: Self-Directed Repair Turns Agent Mistakes Into Lasting Lessons19m◆TACS-RF: Tool-driven Agentic Circuit Synthesis of RF and mmWave Modules19m◆Permission to Retry: A Study of Authorization and Recovery in AI Agent Workflows19m◆Beyond On-Policy vs. Off-Policy: At What Level Should LLM Agent Distillation Follow the Student?19m◆$M^3$: A Multi-LLM System for Multi-Turn Jailbreaking as a Markov Decision Process19m◆Knowing Whom to Trust is not Enough: The Trust--Agreement Gap in Repeated Multi-Party LLM Negotiation19m◆Reproducible Evaluation as the Substrate for Safe Prompt Compression in Production Agents19m◆The Helpful Agent Problem: When Emergent Cooperation Among LLM Agents Bypasses Intended Workflows19m◆CEMIR vs. FISER: a comparative study of reasoning-based and enrichment-based approaches to pragmatic intent recognition19m◆BARC-Bench: Benign Asks, Risky Consequences19m◆RSI-Opt: Recursive Self-Improvement Optimizer Agents For Model Training19m◆PPO vs. SAC: A Comparative Study for Cooperative Motion Control of Dual-Arm Space Robots19m◆Do AI-for-Science Agents Preserve Model Safety?19m◆Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?19m◆HyScale: Scaling Long-Context Training for Learned Sparse Attention19m◆Understanding Communication Failures in Multi-Agent LLM Systems19m◆
News/NightFeats @ MMU-RAGent NeurIPS 2025: A Context-Optimized Multi-Agent RAG System for the Text-to-Text Track
arxiv
PublishedJune 12, 2026 at 4:00 AM
▲bullish

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

Source
arxiv.orgfull article ↗
Read on arxiv→
Publisher summary· verbatim

arXiv:2606.11199v1 Announce Type: cross 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 benchma

Stay posted· Newsletter

Three short emails a week: Monday, Wednesday and Friday. Top movers, new models and the most-referenced story.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Discussion
Mentioned models
03
  • 01
    NightFeats
  • 02
    Claude-SonnetV2
  • 03
    Nova-Pro
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#research#competition#language-models#information-retrieval

No replies yet. Be first.

Mentioned models
03
  • 01
    NightFeats
  • 02
    Claude-SonnetV2
  • 03
    Nova-Pro
Source
↗
arxiv
Read original ↗All from arxiv →
Tags
04
#research#competition#language-models#information-retrieval

Related coverage

More from ARXIV
arxivTradeoff-Aware Territory Design: A Multi-Objective Decision System for Enterprise Customer-to-Seller Allocation19marxivPhronix: The Capability-Centric Learning Paradigm for Agents19marxivPatronizing and Condescending Language Detection in English and Mandarin19marxivPaperFormalizer: Author-in-the-Loop Autoformalization of Research Papers in Lean19m
The Bubble Brief
MON · WED · FRI

Read research insights every Monday, Wednesday and Friday — top movers, new models, story of the week.

// no spam · unsubscribe one-click · free forever

Your email is used only to send The Bubble Brief. Privacy policy

Originally published on arxiv ↗
PrivacyTermsRefundsLegal notice|AboutMethodologyContact

© 2026 Databubble

Built by Marouane Gazouzi · Readyo, AI interview coach

HomeModelsNews