7 papers
RL-Index: Reinforcement Learning for Retrieval Index Reasoning
Yongjia Lei, Nedim Lipka, Zhisheng Qi +7
Retrieving external knowledge is crucial for real-world tasks but remains difficult when queries and relevant knowledge are linked by implicit reasoning (e.g., shared theorems or c…
Infini Memory: Maintainable Topic Documents for Long-Term LLM Agent Memory
Suozhao Ji, Baodong Wu, Zehao Wang +8
Long-term LLM agents need persistent memory that can track changing facts and provide relevant evidence across sessions. Existing memory systems often store observations as isolate…
TRACE: Trajectory Reasoning through Adaptive Cross-Step Evidence Aggregation for LLM Agents
Vijitha Mittapalli, Shreyaa Jayant Dani, Satya Srujana Pilli +7
Autonomous LLM agents can pursue hidden malicious objectives through sequences of individually benign actions, making sabotage difficult to detect using standard trajectory-level m…
Knowledge Homophily in Large Language Models
Utkarsh Sahu, Zhisheng Qi, Mahantesh Halappanavar +6
Large Language Models (LLMs) have been increasingly studied as neural knowledge bases for supporting knowledge-intensive applications such as question answering and fact checking.…
Iterative Critique-Refine Framework for Enhancing LLM Personalization
Durga Prasad Maram, Dhruvin Gandhi, Zonghai Yao +5
Personalized text generation requires models not only to produce coherent text but also to align with a target user's style, tone, and topical focus. Existing retrieval-augmented a…
Forecasting Time Series with LLMs via Patch-Based Prompting and Decomposition
Mayank Bumb, Anshul Vemulapalli, Sri Harsha Vardhan Prasad Jella +7
Recent advances in Large Language Models (LLMs) have demonstrated new possibilities for accurate and efficient time series analysis, but prior work often required heavy fine-tuning…