Related papers: Chain of Unit-Physics: A Primitive-Centric Approac…
As LLMs make their way into many aspects of our lives, one place that warrants increased scrutiny with LLM usage is scientific research. Using LLMs for generating or analyzing data for research purposes is gaining popularity. But when such…
Chain-of-Thought (CoT) is widely applied to enhance the LLM capability in math, coding and reasoning tasks. However, its performance is limited for open-domain tasks, when there are no clearly defined reasoning steps or logical transitions.…
Language-Image Pre-training has demonstrated promising results on zero-shot and few-shot downstream tasks by prompting visual models with natural language prompts. However, most recent studies only use a single prompt for tuning, neglecting…
Deep learning in \emph{de novo} protein design has achieved atomic-level fidelity. However, existing models remain largely non-deliberative: they directly synthesize molecular geometries without explicitly reasoning about which residues or…
Large Language Model (LLM)-based multi-agent systems (MAS) demonstrate remarkable potential for scientific discovery. Existing approaches, however, often automate scientific discovery using predefined workflows that lack rationality…
Recent advances in large language models (LLMs) have enabled progress in agentic coding, where models autonomously reason, plan, and act within interactive software development workflows. However, bridging the gap between static text-based…
Large language models (LLMs) have shown promising potential in scientific research, enabling tasks ranging from knowledge retrieval to property prediction. Existing science benchmarks mainly focus on perceptual or knowledge-based tasks,…
Deploying large language model-based code generation in real-world client-side development remains challenging due to heterogeneous inputs, strict engineering constraints, and complex interaction logic expressed in product requirement…
The advent of large pre-trained language models in the domain of Code Synthesis has shown remarkable performance on various benchmarks, treating the problem of Code Generation in a fashion similar to Natural Language Generation, trained…
Computational materials science and chemistry span vast knowledge domains and fractured software ecosystems. Although large language models (LLMs) have demonstrated research capabilities, scaling monolithic agents to manage the rigor and…
Predictive coding has emerged as an influential normative model of neural computation, with numerous extensions and applications. As such, much effort has been put into mapping PC faithfully onto the cortex, but there are issues that remain…
Large Language Models (LLMs) exhibit remarkable proficiency in addressing a diverse array of tasks within the Natural Language Processing (NLP) domain, with various prompt design strategies significantly augmenting their capabilities.…
While LLMs can effectively help prototype single ML functionalities, many real-world applications involve complex tasks that cannot be easily handled via a single run of an LLM. Recent work has found that chaining multiple LLM runs together…
Autonomous language-model agents are increasingly evaluated on long-horizon tool-use tasks, but existing benchmarks rarely capture the complexity and nuance of real scientific work. To address this gap, we introduce Collider-Bench, a…
Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models. However, its reliability remains largely unexplored beyond English and across diverse model…
Scientific workflows in computational chemistry and materials science typically involve multiple interdependent steps, such as model preparation, system construction, simulation execution, and data analysis, that researchers have refined…
Implicit Chain-of-Thought (CoT) reduces the inference cost of large language models by internalizing the explicit rationales. However, existing approaches typically lack alignment with explicit rationales and adaptivity to example…
The translation of natural language to formal constraint models requires expertise in the problem domain and modeling frameworks. To explore the effectiveness of agentic workflows, we propose CP-Agent, a Python coding agent that uses the…
Rule-based reasoning, a fundamental type of legal reasoning, enables us to draw conclusions by accurately applying a rule to a set of facts. We explore causal language models as rule-based reasoners, specifically with respect to…
As AI agents transition from research prototypes to enterprise production systems, the tool interfaces they consume remain rooted in human-oriented CRUD paradigms. This paper identifies five fundamental architectural mismatches between…