Fengxueyang

LLM-Agent-Paper-Digest. papers related to LLM-agent that published on top conferences

ReHAC. Repo of "Large Language Model-based Human-Agent Collaboration for Complex Task Solving(EMNLP2024 Findings)"

RPEval. This repository is based on our paper "How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants"

GIMO. Optimizing Multi-Turn Interactive Recommendation Agents via Generative Intrinsic Motivation

RetroAct. Repo of Improving Retrospective Language Agents via Joint Policy Gradient Optimization

ECPO. This repository is based on our paper: Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent.