8 papers
Continual Harness: Online Adaptation for Self-Improving Foundation Agents
Seth Karten, Joel Zhang, Tersoo Upaa +5
Coding harnesses such as Claude Code and OpenHands wrap foundation models with tools, memory, and planning, but no equivalent exists for embodied agents' long-horizon partial-obser…
Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning
Chengshuai Shi, Wenzhe Li, Xinran Liang +10
Given the rapidly growing capabilities of vision-language models (VLMs), extending them to interactive decision-making tasks such as video games has emerged as a promising frontier…
MUSIC: MUlti-Step Instruction Contrast for Multi-Turn Reward Models
Wenzhe Li, Shujian Zhang, Wenxuan Zhou +5
Evaluating the quality of multi-turn conversations is crucial for developing capable Large Language Models (LLMs), yet remains a significant challenge, often requiring costly human…
AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following
Yun He, Wenzhe Li, Hejia Zhang +22
Recent progress in large language models (LLMs) has led to impressive performance on a range of tasks, yet advanced instruction following (IF)-especially for complex, multi-turn, a…
LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra
Seth Karten, Wenzhe Li, Zihan Ding +3
We present the LLM Economist, a novel framework that uses agent-based modeling to design and assess economic policies in strategic environments with hierarchical decision-making. A…
MATH-Perturb: Benchmarking LLMs' Math Reasoning Abilities against Hard Perturbations
Kaixuan Huang, Jiacheng Guo, Zihao Li +15
Large language models have demonstrated impressive performance on challenging mathematical reasoning tasks, which has triggered the discussion of whether the performance is achieve…