SalesSim benchmarks MLLMs as retail user simulators, finds gaps in persona adherence and over-persuasion, and introduces UserGRPO RL to raise decision alignment by 13.8%.
Title resolution pending
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
years
2026 6representative citing papers
PRIME enables agents to proactively reason in user-centric tasks by iteratively evolving structured memories from interaction trajectories without gradient-based training.
ActivityEditor introduces a dual-LLM-agent system with reinforcement learning that produces statistically faithful and physically valid human mobility trajectories in zero-shot cross-regional settings.
Iterative Reward Calibration with MT-GRPO and GTPO enables effective multi-turn RL for tool-calling agents, raising Tau-Bench success from 63.8% to 66.7% for a 4B model and from 58.0% to 69.5% for a 30B model.
Step Rejection Fine-Tuning masks loss on erroneous steps identified by a critic LLM in unresolved trajectories, raising SWE-bench Verified resolution rate by 3.7% to 32.2% versus 2.4% for trajectory-level rejection.
The paper delivers the first comprehensive overview of RL for GUI agents, organizing methods into offline, online, and hybrid strategies while analyzing trends in rewards, efficiency, and deliberation to outline a future roadmap.
citing papers explorer
-
SalesSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators
SalesSim benchmarks MLLMs as retail user simulators, finds gaps in persona adherence and over-persuasion, and introduces UserGRPO RL to raise decision alignment by 13.8%.
-
PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent
PRIME enables agents to proactively reason in user-centric tasks by iteratively evolving structured memories from interaction trajectories without gradient-based training.
-
ActivityEditor: Learning to Synthesize Physically Valid Human Mobility
ActivityEditor introduces a dual-LLM-agent system with reinforcement learning that produces statistically faithful and physically valid human mobility trajectories in zero-shot cross-regional settings.
-
Multi-Turn Reinforcement Learning for Tool-Calling Agents with Iterative Reward Calibration
Iterative Reward Calibration with MT-GRPO and GTPO enables effective multi-turn RL for tool-calling agents, raising Tau-Bench success from 63.8% to 66.7% for a 4B model and from 58.0% to 69.5% for a 30B model.
-
Step Rejection Fine-Tuning: A Practical Distillation Recipe
Step Rejection Fine-Tuning masks loss on erroneous steps identified by a critic LLM in unresolved trajectories, raising SWE-bench Verified resolution rate by 3.7% to 32.2% versus 2.4% for trajectory-level rejection.
-
GUI Agents with Reinforcement Learning: Toward Digital Inhabitants
The paper delivers the first comprehensive overview of RL for GUI agents, organizing methods into offline, online, and hybrid strategies while analyzing trends in rewards, efficiency, and deliberation to outline a future roadmap.