arXiv:2604.11544v1 Announce Type: cross Abstract: Structured memory representations such as knowledge graphs are central to autonomous agents and other long-lived systems. However, most existing approaches model time as discrete metadata, either sorting by recency (burying old-yet-permanent knowledge), simply overwriting outdated facts, or requiring an expensive LLM call at every ingestion step, leaving them unable to […]
SciPredict: Can LLMs Predict the Outcomes of Scientific Experiments in Natural Sciences?
arXiv:2604.10718v1 Announce Type: new Abstract: Accelerating scientific discovery requires the identification of which experiments would yield the best outcomes before committing resources to costly physical validation. While existing benchmarks evaluate LLMs on scientific knowledge and reasoning, their ability to predict experimental outcomes – a task where AI could significantly exceed human capabilities – remains largely […]
RTMC: Step-Level Credit Assignment via Rollout Trees
arXiv:2604.11037v1 Announce Type: cross Abstract: Multi-step agentic reinforcement learning benefits from fine-grained credit assignment, yet existing approaches offer limited options: critic-free methods like GRPO assign a uniform advantage to every action in a trajectory, while learned value networks introduce notable overhead and can be fragile under sparse rewards. We observe that group rollouts targeting the […]
TorchUMM: A Unified Multimodal Model Codebase for Evaluation, Analysis, and Post-training
arXiv:2604.10784v1 Announce Type: new Abstract: Recent advances in unified multimodal models (UMMs) have led to a proliferation of architectures capable of understanding, generating, and editing across visual and textual modalities. However, developing a unified framework for UMMs remains challenging due to the diversity of model architectures and the heterogeneity of training paradigms and implementation details. […]
3D-Anchored Lookahead Planning for Persistent Robotic Scene Memory via World-Model-Based MCTS
arXiv:2604.11302v1 Announce Type: cross Abstract: We present 3D-Anchored Lookahead Planning (3D-ALP), a System 2 reasoning engine for robotic manipulation that combines Monte Carlo Tree Search (MCTS) with a 3D-consistent world model as the rollout oracle. Unlike reactive policies that evaluate actions from the current camera frame only, 3D-ALP maintains a persistent camera-to-world (c2w) anchor that […]
Beyond Statistical Co-occurrence: Unlocking Intrinsic Semantics for Tabular Data Clustering
arXiv:2604.10865v1 Announce Type: new Abstract: Deep Clustering (DC) has emerged as a powerful tool for tabular data analysis in real-world domains like finance and healthcare. However, most existing methods rely on data-level statistical co-occurrence to infer the latent metric space, often overlooking the intrinsic semantic knowledge encapsulated in feature names and values. As a result, […]
Pyramid MoA: A Probabilistic Framework for Cost-Optimized Anytime Inference
arXiv:2602.19509v3 Announce Type: replace-cross Abstract: We observe that LLM cascading and routing implicitly solves an anytime computation problem — a class of algorithms, well-studied in classical AI, that improve solutions as additional computation is allocated. We formalize this connection and propose Pyramid MoA, a hierarchical Mixture-of-Agents architecture governed by a decision-theoretic router that escalates queries […]
Reasoning as Data: Representation-Computation Unity and Its Implementation in a Domain-Algebraic Inference Engine
arXiv:2604.10908v1 Announce Type: new Abstract: Every existing knowledge system separates storage from computation. We show this separation is unnecessary and eliminate it. In a standard triple is_a(Apple, Company), domain context lives in the query or the programmer’s mind. In a CDC four-tuple is_a(Apple, Company, @Business), domain becomes a structural field embedded in predicate arity. Any […]
Harnessing Photonics for Machine Intelligence
arXiv:2604.10841v1 Announce Type: cross Abstract: The exponential growth of machine-intelligence workloads is colliding with the power, memory, and interconnect limits of the post-Moore era, motivating compute substrates that scale beyond transistor density alone. Integrated photonics is emerging as a candidate for artificial intelligence (AI) acceleration by exploiting optical bandwidth and parallelism to reshape data movement […]
CROP: Conservative Reward for Model-based Offline Policy Optimization
arXiv:2310.17245v2 Announce Type: replace-cross Abstract: Offline reinforcement learning (RL) aims to optimize a policy using collected data without online interactions. Model-based approaches are particularly appealing for addressing offline RL challenges because of their capability to mitigate the limitations of data coverage through data generation using models. Nonetheless, a prevalent issue in offline RL is the […]
Back to the Barn with LLAMAs: Evolving Pretrained LLM Backbones in Finetuning Vision Language Models
arXiv:2604.10985v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have rapidly advanced by leveraging powerful pre-trained Large Language Models (LLMs) as core reasoning backbones. As new and more capable LLMs emerge with improved reasoning, instruction-following, and generalization, there is a pressing need to efficiently update existing VLMs to incorporate these advancements. However, the integration of new […]
Sanity Checks for Agentic Data Science
arXiv:2604.11003v1 Announce Type: new Abstract: Agentic data science (ADS) pipelines have grown rapidly in both capability and adoption, with systems such as OpenAI Codex now able to directly analyze datasets and produce answers to statistical questions. However, these systems can reach falsely optimistic conclusions that are difficult for users to detect. To address this, we […]