11 papers
MemCodex: Self-Programming Hierarchical Memory for Language Agents
Xiaoqiang Wang, Bang Liu
Agent memory faces heterogeneous access needs: a single-hop question may require one piece of evidence, whereas a multi-hop question must combine evidence from multiple sources. Pr…
LatentHarness: Learning Latent Actions for Memory and Reasoning via Counterfactual Policy Distillation
Xiaoqiang Wang, Suyuchen Wang, Bang Liu
Long-context reasoning faces two complementary bottlenecks: retaining evidence across long inputs and sustaining computation across many reasoning steps. Existing approaches largel…
Foundation Protocol: A Coordination Layer for Agentic Society
Bang Liu, Yongfeng Gu, Jiayi Zhang +26
Autonomous agents are moving from tools into a layer of social infrastructure: they browse, purchase, deploy software, manage systems, and increasingly interact with one another. A…
IntentionNav: A Benchmark for Intent-Driven Object Navigation from Implicit Human Instruction
Lin Qian, Shijie Li, Sihao Lin +4
Existing object navigation benchmarks usually tell an embodied agent which object category to find, such as microwave or chair. Human-facing embodied AI is often asked something le…
Mem-: Adaptive Memory through Learning When and What to Generate
Xiaoqiang Wang, Chao Wang, Hadi Nekoei +5
We present Mem-, a framework for adaptive memory in large language model (LLM) agents, where useful guidance is generated on demand rather than retrieved from external memory st…
Latent Action Reparameterization for Efficient Agent Inference
Wenhao Huang, Qingwen Zeng, Qiyue Chen +11
Large language model (LLM) agents often rely on long sequences of low-level textual actions, resulting in large effective decision horizons and high inference cost. While prior wor…
Scalable Environments Drive Generalizable Agents
Jiayi Zhang, Fanqi Kong, Guibin Zhang +7
Generalizable agents should adapt to diverse tasks and unseen environments beyond their training distribution. This position paper argues that such generalization requires environm…
System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts
Xiaoqiang Wang, Suyuchen Wang, Yun Zhu +1
Chain-of-thought (CoT) reasoning enables large language models (LLMs) to move beyond fast System-1 responses and engage in deliberative System-2 reasoning. However, this comes at t…
RMem: Bridging Memory Retention and Retrieval via Reversible Compression
Xiaoqiang Wang, Suyuchen Wang, Yun Zhu +1
Memory plays a key role in enhancing LLMs' performance when deployed to real-world applications. Existing solutions face trade-offs: explicit memory designs based on external stora…
OSCAR: Operating System Control via State-Aware Reasoning and Re-Planning
Xiaoqiang Wang, Bang Liu
Large language models (LLMs) and large multimodal models (LMMs) have shown great potential in automating complex tasks like web browsing and gaming. However, their ability to gener…
FACE: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition
Xiaoqiang Wang, Lingfei Wu, Tengfei Ma +1
Large language models (LLMs) are primarily evaluated by overall performance on various text understanding and generation tasks. However, such a paradigm fails to comprehensively di…