Related papers: Discover and Prove: An Open-source Agentic Framewo…
Large Language Model (LLM) agents are deployed in complex environments -- such as massive codebases, enterprise databases, and conversational histories -- where the relevant state far exceeds their context windows. To navigate these spaces,…
How can we use AI to discover a new state of the art for a scientific problem? Prior work in test-time scaling, such as AlphaEvolve, performs search by prompting a frozen LLM. We perform reinforcement learning at test time, so the LLM can…
Large Language Models (LLMs) are increasingly excelling and outpacing human performance on many tasks. However, to improve LLM reasoning, researchers either rely on ad-hoc generated datasets or formal mathematical proof systems such as the…
Language models have become increasingly powerful tools for formal mathematical reasoning. However, most existing approaches rely exclusively on either large general-purpose models or smaller specialized models, each with distinct…
Automated Theorem Proving (ATP) deals with the development of computer programs being able to show that some conjectures (queries) are a logical consequence of a set of axioms (facts and rules). There exists several successful ATPs where…
LLMs have made significant progress in complex but easy-to-verify problems, yet they still struggle with discovering the unknown. In this paper, we present \textbf{AlphaResearch}, an autonomous research agent designed to discover new…
We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address…
Methodologies for development of complex systems and models include external reviews by domain and technology experts. Among others, such reviews can uncover undocumented built-in assumptions that may be critical for correct and safe…
Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…
Can the rapid advances in code generation, function calling, and data analysis using large language models (LLMs) help automate the search and verification of hypotheses purely from a set of provided datasets? To evaluate this question, we…
The advancements of large language models (LLMs) have piqued growing interest in developing LLM-based language agents to automate scientific discovery end-to-end, which has sparked both excitement and skepticism about their true…
Many inference-time language-model pipelines combine a cheap reward signal with an expensive verifier, such as exact answer checking in mathematical reasoning or hidden-test execution in code generation. We formalize this setting using a…
Architectural tactics (ATs), as the concrete implementation of architectural decisions in code, address non-functional requirements of software systems. Due to the implicit nature of architectural knowledge in code implementation,…
The rise of Agentic applications and automation in the Voice AI industry has led to an increased reliance on Large Language Models (LLMs) to navigate graph-based logic workflows composed of nodes and edges. However, existing methods face…
Answer set programming (ASP) and planning are two widely used paradigms for solving logic programs with declarative programming. In both cases, the quality of the input programs has a major influence on the quality and performance of the…
Large language models are increasingly deployed as specialized agents that plan, call tools, and take actions over extended horizons. Yet many existing evaluations assume a "clean interface" where dynamics are specified and stable, tools…
The most promising recent methods for AI reasoning require applying variants of reinforcement learning (RL) either on rolled out trajectories from the LLMs, even for the step-wise rewards, or large quantities of human-annotated trajectory…
Prompt engineering for LLMs remains complex, with existing frameworks either hiding complexity behind restrictive APIs or providing inflexible canned patterns that resist customization -- making sophisticated agentic programming…
Evaluating agentic AI on open-ended professional tasks faces a fundamental dilemma between rigor and flexibility. Static rubrics provide rigorous, reproducible assessment but fail to accommodate diverse valid response strategies, while…
Answer Set Programming (ASP) is a powerful declarative programming paradigm commonly used for solving challenging search and optimization problems. The modeling languages of ASP are supported by sophisticated solving algorithms (solvers)…