Related papers: Discover and Prove: An Open-source Agentic Framewo…

Automated theorem proving is fundamental to formal methods, and the recent trend is to integrate large language models (LLMs) and proof assistants to form effective proof agents. While existing proof agents show promising performance, they…

Recent advances in large language models (LLMs) have propelled research in natural language interfaces to databases. However, most state-of-the-art text-to-SQL systems still depend on complex, multi-stage pipelines. This work proposes a…

Existing evaluation frameworks for large language models -- including HELM, MT-Bench, AgentBench, and BIG-bench -- are designed for controlled, single-session, lab-scale settings. They do not address the evaluation challenges that emerge…

While Large Language Models (LLMs) have evolved into tool-using agents, they remain brittle in long-horizon interactions. Unlike mathematical reasoning where errors are often rectifiable via backtracking, tool-use failures frequently induce…

Large reasoning models, such as OpenAI o1 and DeepSeek-R1, tend to become increasingly verbose as their reasoning capabilities improve. These inflated Chain-of-Thought (CoT) trajectories often exceed what the underlying problems require,…

The integration of Large Language Models (LLMs) into healthcare is constrained by knowledge limitations, hallucinations, and a disconnect from Evidence-Based Medicine (EBM). While Retrieval-Augmented Generation (RAG) offers a solution,…

Artificial intelligence is reshaping scientific exploration, but most methods automate procedural tasks without engaging in scientific reasoning, limiting autonomy in discovery. We introduce Materials Agents for Simulation and Theory in…

Multi-agent frameworks promise to simplify LLM-driven software development, yet there is no principled way to evaluate their developer experience in a controlled setting. We introduce DDL2PropBank, a novel benchmark task that maps…

AI agents powered by large language models (LLMs) are being used to solve increasingly complex software engineering challenges, but struggle with hardware design tasks. Register Transfer Level (RTL) code presents a unique challenge for…

Recent large language models (LLMs) have achieved impressive reasoning milestones but continue to struggle with high computational costs, logical inconsistencies, and sharp performance degradation on high-complexity problems. While…

Ensuring the safety of large language models (LLMs) is paramount, yet identifying potential vulnerabilities is challenging. While manual red teaming is effective, it is time-consuming, costly and lacks scalability. Automated red teaming…

Autonomous data science, from raw data sources to analyst-grade deep research reports, has been a long-standing challenge, and is now becoming feasible with the emergence of powerful large language models (LLMs). Recent workflow-based data…

We present StepFun-Prover Preview, a large language model designed for formal theorem proving through tool-integrated reasoning. Using a reinforcement learning pipeline that incorporates tool-based interactions, StepFun-Prover can achieve…

Formal mathematical reasoning remains a critical challenge for artificial intelligence, hindered by limitations of existing benchmarks in scope and scale. To address this, we present FormalMATH, a large-scale Lean4 benchmark comprising…

We study mathematical discovery through the lens of neurosymbolic reasoning, where an AI agent powered by a large language model (LLM), coupled with symbolic computation tools, and human strategic direction, jointly produced a new result in…

Although Long Reasoning Models (LRMs) have achieved superior performance on various reasoning scenarios, they often suffer from increased computational costs and inference latency caused by overthinking. To address these limitations, we…

With the rapid advancement of agent-based methods in recent years, Agentic RAG has undoubtedly become an important research direction. Multi-hop reasoning, which requires models to engage in deliberate thinking and multi-step interaction,…

Large Language Model (LLM)-based agentic systems rely on in-context policy documents encoding diverse business rules. As requirements grow, these documents expand rapidly, causing high computational overhead. This motivates developing…

Large language models (LLMs) have recently shown strong progress on scientific reasoning, yet two major bottlenecks remain. First, explicit retrieval fragments reasoning, imposing a hidden "tool tax" of extra tokens and steps. Second,…

Multi-hop questions still stump large language models (LLMs), which struggle to link information across multiple reasoning steps. We introduce Auto-Patch, a novel method that dynamically patches hidden states during inference to enhance…