9 papers
DarwinX: Evolving Agent Harnesses Through Natural Selection
Yifan Zhang, Yutong Dai, Juntao Tan +9
An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control flow. Self-improvement loops already edit harnesses, yet single-…
Aligning Deep Implicit Preferences by Learning to Reason Defensively
Peiming Li, Zhiyuan Hu, Yang Tang +2
Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they…
Physical Plausibility Reasoning via HCM-GRPO: Empowering Compact Model for Superior Performance
Zhiyuan Hu, Zheng Sun, Yi Wei +1
The performance of image generation has been significantly improved in recent years. However, the study of image screening is rare, and its performance with Multimodal Large Langua…
ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenders
Ofer Meshi, Krisztian Balog, Sally Goldman +5
The promise of LLM-based user simulators to improve conversational AI is hindered by a critical "realism gap," leading to systems that are optimized for simulated interactions, but…
EvoClinician: A Self-Evolving Agent for Multi-Turn Medical Diagnosis via Test-Time Evolutionary Learning
Yufei He, Juncheng Liu, Zhiyuan Hu +9
Prevailing medical AI operates on an unrealistic ''one-shot'' model, diagnosing from a complete patient file. However, real-world diagnosis is an iterative inquiry where Clinicians…
Rewarding the Rare: Uniqueness-Aware RL for Creative Problem Solving in LLMs
Zhiyuan Hu, Yucheng Wang, Yufei He +7
Reinforcement learning (RL) has become a central paradigm for post-training large language models (LLMs), particularly for complex reasoning tasks, yet it often suffers from explor…