Related papers: Thinking Longer, Not Larger: Enhancing Software En…

Large Language Models (LLMs) were shown to struggle with long-term planning, which may be caused by the limited way in which they explore the space of possible solutions. We propose an architecture where a Reinforcement Learning (RL) Agent…

Evaluating the capabilities and risks of foundation models is paramount, yet current methods demand extensive domain expertise, hindering their scalability as these models rapidly evolve. We introduce SKATE: a novel evaluation framework in…

Large language models (LLMs) exhibit strong performance on self-contained programming tasks. However, they still struggle with repository-level software engineering (SWE), which demands (1) deep codebase navigation with effective context…

Sequential test-time scaling is a promising training-free method to improve large reasoning model accuracy, but as currently implemented, significant limitations have been observed. Inducing models to think for longer can increase their…

Large Language Model (LLM) agents can increasingly automate complex reasoning through Test-Time Scaling (TTS), iterative refinement guided by reward signals. However, many real-world tasks involve multi-stage pipeline whose final outcomes…

Progress on training and architecture strategies has enabled LLMs with millions of tokens in context length. However, empirical evidence suggests that such long-context LLMs can consume far more text than they can reliably use. On the other…

Reasoning reinforcement learning (RL) has recently revealed a new scaling effect: test-time scaling. Thinking models such as R1 and o1 improve their reasoning accuracy at test time as the length of the reasoning context increases. However,…

Recent deep research agents primarily improve performance by scaling reasoning depth, but this leads to high inference cost and latency in search-intensive scenarios. Moreover, generalization across heterogeneous research settings remains…

Recent advances in Large Language Models (LLMs) have demonstrated remarkable performance in Contextual Question Answering (CQA). However, prior approaches typically employ elaborate reasoning strategies regardless of question complexity,…

Large Language Models (LLMs) often struggle with computational efficiency and error propagation in multi-step reasoning tasks. While recent advancements on prompting and post-training have enabled LLMs to perform step-wise reasoning, they…

Large Language Models (LLMs) have become widely used for Software Engineering (SE) tasks, spanning from function-level code generation to complex repository-level workflows. However, the high latency of autoregressive inference remains a…

Large language models (LLMs) have demonstrated impressive reasoning capabilities when provided with chain-of-thought exemplars, but curating large reasoning datasets remains laborious and resource-intensive. In this work, we introduce…

Human reasoning is shaped by resource rationality -- optimizing performance under constraints. Recently, inference-time scaling has emerged as a powerful paradigm to improve the reasoning performance of Large Language Models by expanding…

Large Reasoning Models (LRMs) achieve strong performance on mathematical reasoning tasks but remain unreliable on challenging instances. Existing test-time scaling methods, such as repeated sampling, self-correction, and tree search,…

In large language models (LLMs), code and reasoning reinforce each other: code offers an abstract, modular, and logic-driven structure that supports reasoning, while reasoning translates high-level goals into smaller, executable steps that…

The central challenge of AI for Science is not reasoning alone, but the ability to create computational methods in an open-ended scientific world. Existing LLM-based agents rely on static, pre-defined tool libraries, a paradigm that…

Software engineering (SWE) agents are transitioning from code generation to full software development lifecycle automation. A critical phase in this lifecycle is specification design: transforming initial proposals into carefully considered…

Associative memory has long underpinned the design of sequential models. Beyond recall, humans reason by projecting future states and selecting goal-directed actions, a capability that modern language models increasingly require but do not…

Large language models (LLMs) struggle with complex, long-horizon reasoning due to instability caused by their frozen policy assumption. Current test-time scaling methods treat execution feedback merely as an external signal for filtering or…

Code generation, the task of creating executable programs from natural language requirements, has recently seen tremendous advances through Chain-of-Thought (CoT) reasoning, which enables Large Language Models (LLMs) to develop high-level…