Related papers: MemCompiler: Compile, Don't Inject -- State-Condit…
To enable embodied agents to operate effectively over extended timeframes, it is crucial to develop models that form and access memories to stay contextualized in their environment. In the current paradigm of training transformer-based…
Existing memory systems for language agents address memory management: how to retrieve and page more information within a context budget. We address a complementary problem -- memory utility: what experience is worth keeping, and how it…
Embedded systems have proliferated in various consumer and industrial applications with the evolution of Cyber-Physical Systems and the Internet of Things. These systems are subjected to stringent constraints so that embedded software must…
Despite rapid progress in large-scale language and vision models, AI agents still suffer from a fundamental limitation: they cannot remember. Without reliable memory, agents catastrophically forget past experiences, struggle with…
While "Intent-oriented programming" (or "Vibe Coding") redefines software engineering, existing code agents remain tethered to static code snapshots. Consequently, they struggle to model the critical information embedded in the temporal…
Foundation models rely on in-context learning for personalized decision making. The limited size of this context window necessitates memory compression and retrieval systems like RAG. These systems however often treat memory as large…
Compiler optimization is crucial for enhancing program performance by transforming the sequence of optimization passes while maintaining correctness. Despite the promising potential of large language models (LLMs)-based agent for software…
LLM-powered embodied agents have shown success on conventional object-rearrangement tasks, but providing personalized assistance that leverages user-specific knowledge from past interactions presents new challenges. We investigate these…
To tackle long-context reasoning tasks without the quadratic complexity of standard attention mechanisms, approaches based on agent memory have emerged, which typically maintain a dynamically updated memory when linearly processing document…
Given a simple request like Put a washed apple in the kitchen fridge, humans can reason in purely abstract terms by imagining action sequences and scoring their likelihood of success, prototypicality, and efficiency, all without moving a…
GUI agents are beginning to operate the web, mobile, and desktop as interactive worlds, where successful control depends on carrying forward visual, procedural, and task-level evidence beyond the fleeting present screen. Yet most agents…
Embodied agents are evolving from passive reasoning systems into active executors that interact with tools, robots, and physical environments. Once granted execution authority, the central challenge becomes how to keep actions governable at…
Image processing and machine learning applications benefit tremendously from hardware acceleration, but existing compilers target either FPGAs, which sacrifice power and performance for flexible hardware, or ASICs, which rapidly become…
In many, if not every realistic sequential decision-making task, the decision-making agent is not able to model the full complexity of the world. The environment is often much larger and more complex than the agent, a setting also known as…
Complex reasoning in tool-augmented agent frameworks is inherently long-horizon, causing reasoning traces and transient tool artifacts to accumulate and strain the bounded working context of large language models. Without explicit memory…
Recent GUI agents have made substantial progress in visual grounding and action prediction, yet they remain brittle in long-horizon tasks that require maintaining task state across many interface transitions. Existing agents typically rely…
Procedural memory enables large language model (LLM) agents to internalize "how-to" knowledge, theoretically reducing redundant trial-and-error. However, existing frameworks predominantly suffer from a "passive accumulation" paradigm,…
Long-running AI agents need persistent memory. Memory supports learning across sessions, reduces repeated context injection, and enables auditing of past decisions. Current agent memory systems and database paradigms treat memory as…
Embodied intelligence aims to enable robots to learn, reason, and generalize robustly across complex real-world environments. However, existing approaches often struggle with partial observability, fragmented spatial reasoning, and…
We introduce Compositional Imitation Learning and Execution (CompILE): a framework for learning reusable, variable-length segments of hierarchically-structured behavior from demonstration data. CompILE uses a novel unsupervised,…