TurnFlow: Benchmarking User-State Reasoning in Multi-Turn LLM Agents via Scene-Guided User Simulation
cs.AI
Submitted: 2026-11-07
Updated: 2026-11-07
Project page: https://x-easys.github.io/TurnFlow
Terminology
Sources
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference
- Multi-IF: Benchmarking LLMs on Multi-Turn and Multilingual Instructions Following
- AMemGym: Interactive Memory Benchmarking for Assistants in Long-Horizon Conversations
- LLMs Get Lost In Multi-Turn Conversation
- COMPASS: Benchmarking Constrained Optimization in LLM Agents
- AgentChangeBench: A Multi-Dimensional Evaluation Framework for Goal-Shift Robustness in Conversational AI
- Kimi K2.5: Visual Agentic Intelligence
- LLM-based Human Simulations Have Not Yet Been Reliable
- LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory
- Qwen3 Technical Report
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
- GLM-5: from Vibe Coding to Agentic Engineering
- WildChat: 1M ChatGPT Interaction Logs in the Wild
- Instruction-Following Evaluation for Large Language Models
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents