6 papers
MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks
Zexue He, Yu Wang, Churan Zhi +11
Existing evaluations of agents with memory typically assess memorization and action in isolation. One class of benchmarks evaluates memorization by testing recall of past conversat…
The AI Hippocampus: How Far are We From Human Memory?
Zixia Jia, Jiaqi Li, Yipeng Kang +12
Memory plays a foundational role in augmenting the reasoning, adaptability, and contextual fidelity of modern Large Language Models and Multi-Modal LLMs. As these models transition…
Reinforced Embodied Planning with Verifiable Reward for Real-World Robotic Manipulation
Zitong Bo, Yue Hu, Jinming Ma +7
Enabling robots to execute long-horizon manipulation tasks from free-form language instructions remains a fundamental challenge in embodied AI. While vision-language models (VLMs)…
Seek in the Dark: Reasoning via Test-Time Instance-Level Policy Gradient in Latent Space
Hengli Li, Chenxi Li, Tong Wu +8
Reasoning ability, a core component of human intelligence, continues to pose a significant challenge for Large Language Models (LLMs) in the pursuit of AGI. Although model performa…
Absolute Zero: Reinforced Self-play Reasoning with Zero Data
Andrew Zhao, Yiran Wu, Yang Yue +7
Reinforcement learning with verifiable rewards (RLVR) has shown promise in enhancing the reasoning capabilities of large language models by learning directly from outcome-based rew…
The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents
Feiran Jia, Tong Wu, Xin Qin +1
Large Language Model (LLM) agents are increasingly being deployed as conversational assistants capable of performing complex real-world tasks through tool integration. This enhance…