8 papers
Structure-Aware Semantic Chunking with Title-Chain Prefixes: A 1600-Query Evaluation and the Measurement Trap in Text-Transform Ablations
Yang Yang
Chunking is the first and most consequential step in retrieval-augmented generation (RAG): every downstream retrieval decision inherits the chunk boundaries. We present a three-sta…
SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents
Wenxuan Wang, Haoyu Sun, Fukuan Hou +4
Persistent AI assistants, such as OpenClaw, accumulate large collections of related memories over long-term interactions. As these memories grow, they may reinforce one another, di…
Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents
Haoyu Sun, Wenxuan Wang, Mingyang Song +5
Planning is central to LLM agents: before acting, an agent must decompose goals, select tools, reason over constraints, and decide when a task is infeasible. Yet existing agent eva…
MAPGD: Multi-Agent Prompt Gradient Descent for Collaborative Prompt Optimization
Yichen Han, Yuhang Han, Siteng Huang +7
Prompt engineering is crucial for fully leveraging large language models (LLMs), yet most existing optimization methods follow a single trajectory, resulting in limited adaptabilit…
THOR: Transformer Heuristics for On-Demand Retrieval
Isaac Shi, Zeyuan Li, Fan Liu +4
We introduce the THOR (Transformer Heuristics for On-Demand Retrieval) Module, designed and implemented by eSapiens, a secure, scalable engine that transforms natural-language ques…
eSapiens's DEREK Module: Deep Extraction & Reasoning Engine for Knowledge with LLMs
Isaac Shi, Zeyuan Li, Fan Liu +4
We present the DEREK (Deep Extraction & Reasoning Engine for Knowledge) Module, a secure and scalable Retrieval-Augmented Generation pipeline designed specifically for enterprise d…