Related papers: SIA: Self Improving AI with Harness & Weight Updat…
The objective of this study is to improve automated feedback tools designed for English Language Learners (ELLs) through the utilization of data science techniques encompassing machine learning, natural language processing, and educational…
As more and more AI agents are used in practice, it is time to think about how to make these agents fully autonomous so that they can learn by themselves in a self-motivated and self-supervised manner rather than being retrained…
Accurate auto-formalization of theorem statements is essential for advancing automated discovery and verification of research-level mathematics, yet remains a major bottleneck for LLMs due to hallucinations, semantic mismatches, and their…
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-observability decision-making. We first report our Gemini Plays…
The exponential growth of academic publications poses challenges for the research process, such as literature review and procedural planning. Large Language Models (LLMs) have emerged as powerful AI tools, especially when combined with…
Recursive self-improvement is moving from theory to practice: modern systems can critique, revise, and evaluate their own outputs, yet iterative self-modification risks subtle alignment drift. We introduce SAHOO, a practical framework to…
Existing multimodal search agents process target entities sequentially, issuing one tool call per entity and accumulating redundant interaction rounds whenever a query decomposes into independent sub-retrievals. We argue that effective…
While large language models (LLMs) have demonstrated remarkable versatility across a wide range of general tasks, their effectiveness often diminishes in domain-specific applications due to inherent knowledge gaps. Moreover, their…
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 systems increasingly automate pieces of AI research. Yet turning underspecified research objectives into runnable, experimentally validated ML systems remains a central bottleneck. We study this operational setting as…
Academic advising in higher education is under severe strain, with advisor-to-student ratios commonly exceeding 300:1. These structural bottlenecks limit timely access to guidance, increase the risk of delayed graduation, and contribute to…
Long-term memory is becoming a central bottleneck for language agents. Exsting RAG and GraphRAG systems largely treat memory graphs as static retrieval middleware, which limits their ability to recover complete evidence chains from partial…
AI's rapid growth has been felt acutely by scholarly venues, leading to growing pains within the peer review process. These challenges largely center on the inability of specific subareas to identify and evaluate work that is appropriate…
The dominant paradigm for improving mathematical reasoning in language models relies on Reinforcement Learning with verifiable rewards. Yet existing methods treat each problem instance in isolation without leveraging the reusable strategies…
The full potential of large pretrained models remains largely untapped in control domains like robotics. This is mainly because of the scarcity of data and the computational challenges associated with training or fine-tuning these large…
LLM agents hold significant promise for advancing scientific research. To accelerate this progress, we introduce AIRS-Bench (the AI Research Science Benchmark), a suite of 20 tasks sourced from state-of-the-art machine learning papers.…
The goal of the present paper is to develop and validate a questionnaire to assess AI literacy. In particular, the questionnaire should be deeply grounded in the existing literature on AI literacy, should be modular (i.e., including…
Ideally, we would place a robot in a real-world environment and leave it there improving on its own by gathering more experience autonomously. However, algorithms for autonomous robotic learning have been challenging to realize in the real…
Open-ended self-improving agents can autonomously modify their own structural designs to advance their capabilities and overcome the limits of pre-defined architectures, thus reducing reliance on human intervention. We introduce…
Harnesses are now central to coding-agent performance, mediating how models interact with tools and execution environments. Yet harness engineering remains a manual craft, because automating it faces a heterogeneous action space across…