7 papers
When Does Memory Help Multi-Trajectory Inference for Tool-Use LLM Agents?
Xinzhe Li, Yaguang Tao
Multi-trajectory inference for tool-use LLM agents - generating multiple reasoning attempts and selecting among them - benefits from transferring knowledge across attempts so that…
LiTS: A Modular Framework for LLM Tree Search
Xinzhe Li, Yaguang Tao
LiTS is a modular Python framework for LLM reasoning via tree search. It decomposes tree search into three reusable components (Policy, Transition, and RewardModel) that plug into…
Chain-in-Tree: Back to Sequential Reasoning in LLM Tree Search
Xinzhe Li
Test-time scaling improves large language models (LLMs) on long-horizon reasoning tasks by allocating more compute at inference. LLM inference via tree search (LITS) achieves stron…
A Survey on LLM Test-Time Compute via Search: Tasks, LLM Profiling, Search Algorithms, and Relevant Frameworks
Xinzhe Li
LLM test-time compute (or LLM inference) via search has emerged as a promising research area with rapid developments. However, current frameworks often adopt distinct perspectives…
A Review of Prominent Paradigms for LLM-Based Agents: Tool Use (Including RAG), Planning, and Feedback Learning
Xinzhe Li
Tool use, planning, and feedback learning are currently three prominent paradigms for developing Large Language Model (LLM)-based agents across various tasks. Although numerous fra…
GRAMMAR: Grounded and Modular Methodology for Assessment of Closed-Domain Retrieval-Augmented Language Model
Xinzhe Li, Ming Liu, Shang Gao
Retrieval-Augmented Generation (RAG) systems are widely used across various industries for querying closed-domain and in-house knowledge bases. However, evaluating these systems pr…