Related papers: Continual Harness: Online Adaptation for Self-Impr…

We introduce a modular harness design for LLM agents that composes of perception, memory, and reasoning components, enabling a single LLM or VLM backbone to tackle a wide spectrum of multi turn gaming environments without domain-specific…

Pokemon Red is a long-horizon JRPG with sparse rewards, partial observability, and quirky control mechanics that make it a challenging benchmark for reinforcement learning. While recent work has shown that PPO agents can clear the first two…

Building embodied agents on integrating Large Language Models (LLMs) and Reinforcement Learning (RL) have revolutionized human-AI interaction: researchers can now leverage language instructions to plan decision-making for open-ended tasks.…

The rapid advancement of large language models (LLMs) has significantly enhanced the capabilities of AI-driven agents across various tasks. However, existing agentic systems, whether based on fixed pipeline algorithms or pre-defined…

Foundation models have transformed automated code generation, yet autonomous software-engineering agents remain unreliable in realistic development settings. The dominant explanation locates this gap in model capability. We propose a…

AI-native software development is often evaluated at the level of individual models, prompts, or generated artifacts. This framing is insufficient for production environments where software must be continuously produced, verified, deployed,…

Affordance grounding requires identifying where and how an agent should interact in open-world scenes, where actionable regions are often small, occluded, reflective, and visually ambiguous. Recent systems therefore combine multiple skills…

G\"odel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop. We introduce Polaris, a G\"odel agent for compact models that performs policy repair via…

LLM agents increasingly operate in open-ended environments spanning hundreds of sequential episodes, yet they remain largely stateless: each task is solved from scratch without converting past experience into better future behavior. The…

Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool…

Agent-compiled knowledge bases provide persistent external knowledge for large language model (LLM) agents in open-ended, knowledge-intensive downstream tasks. Yet their quality is systematically limited by \emph{incompleteness},…

AI agent frameworks operate in isolation, forcing agents to rediscover solutions and repeat mistakes across different systems. Despite valuable problem-solving experiences accumulated by frameworks like smolagents, OpenHands, and OWL, this…

Pre-trained and frozen large language models (LLMs) can effectively map simple scene rearrangement instructions to programs over a robot's visuomotor functions through appropriate few-shot example prompting. To parse open-domain natural…

Solving an NP-hard optimization problem often requires reformulating it for a specific solver -- quantum hardware, a commercial optimizer, or a domain heuristic. A tool for polynomial-time reductions between hard problems would let…

Optimizing large-scale machine learning systems, such as recommendation models for global video platforms, requires navigating a massive hyperparameter search space and, more critically, designing sophisticated optimizers, architectures,…

The field of Embodied AI is witnessing a rapid evolution toward general-purpose robotic systems, fueled by high-fidelity simulation and large-scale data collection. However, this scaling capability remains severely bottlenecked by a…

Agentic AI systems use specialized agents to handle tasks within complex workflows, enabling automation and efficiency. However, optimizing these systems often requires labor-intensive, manual adjustments to refine roles, tasks, and…

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…

Self-improving AI systems aim to reduce reliance on human engineering by learning to improve their own learning and problem-solving processes. Existing approaches to self-improvement rely on fixed, handcrafted meta-level mechanisms,…

Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters. In this work, we investigate strategies to endow agents with a…