TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives
cs.AI
Submitted: 2026-09-17
Updated: 2026-09-17
Journal ref: 35th ACM International Conference on Information and Knowledge Management (CIKM 2026), Nov 2026, Rome, Italy
Code: https://github.com/Kepler1908/TRACE
Project page: https://mezanno.xyz
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- MTRACE: Multilingual Retrieval-Augmented Generation for Temporally Diverse Text Corpora
- MA-RAG: Multi-Agent Retrieval-Augmented Generation via Collaborative Chain-of-Thought Reasoning
- Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
- Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training
- ReAct: Synergizing Reasoning and Acting in Language Models
- WeatherArchive-Bench: Benchmarking Retrieval-Augmented Reasoning for Historical Weather Archives
- OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation
- Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
- LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora
- Question Decomposition for Retrieval-Augmented Generation
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
- RAGentA: Multi-Agent Retrieval-Augmented Generation for Attributed Question Answering
- DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
- A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfaces
- From Local to Global: A Graph RAG Approach to Query-Focused Summarization
- Research on Graph-Retrieval Augmented Generation Based on Historical Text Knowledge Graphs
- LightRAG: Simple and Fast Retrieval-Augmented Generation
- From RAG to Memory: Non-Parametric Continual Learning for Large Language Models
- Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrieval
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection