Related papers: Teaching Language Models to Think in Code
Large Language Models (LLMs) are increasingly integrated into the software engineering ecosystem. Their test-time compute (TTC) reasoning capabilities show significant potential for understanding program logic and semantics beyond mere…
Large Language Models have achieved impressive performance on reasoning-intensive tasks, yet optimizing their reasoning efficiency remains an open challenge. While Test-Time Scaling (TTS) improves reasoning quality, it often leads to…
Chain-of-thought (CoT) reasoning has enabled transformer-based language models to excel at complex mathematics and multi-step planning. However, in standard decoder-only architectures, these reasoning steps are externalized in natural…
Inductive reasoning is a core component of human intelligence. In the past research of inductive reasoning within computer science, formal language is used as representations of knowledge (facts and rules, more specifically). However,…
The Abstraction and Reasoning Corpus (ARC) provides a compact laboratory for studying abstract reasoning, an ability central to human intelligence. Modern AI systems, including LLMs and ViTs, largely operate as sequence-of-behavior…
Inductive program synthesis, or programming by example, requires synthesizing functions from input-output examples that generalize to unseen inputs. While large language model agents have shown promise in programming tasks guided by natural…
Long chain-of-thought (CoT) significantly enhances the reasoning capabilities of large language models (LLMs). However, extensive reasoning traces lead to inefficiencies and increased time-to-first-token (TTFT). We propose a training…
Code reasoning is a fundamental capability for large language models (LLMs) in the code domain. It involves understanding and predicting a program's execution behavior, such as determining the output for a given input or whether a specific…
Recent works have shown great potentials of Large Language Models (LLMs) in robot task and motion planning (TAMP). Current LLM approaches generate text- or code-based reasoning chains with sub-goals and action plans. However, they do not…
Large Language Models (LLMs) can achieve enhanced complex problem-solving through test-time computing scaling, yet this often entails longer contexts and numerous reasoning token costs. In this paper, we propose an efficient test-time…
Large language models (LLMs) empowered by chain-of-thought reasoning have achieved impressive accuracy on complex tasks but suffer from excessive inference costs and latency when applied uniformly to all problems. We propose SABER…
Test-time Training enables model adaptation using only test questions and offers a promising paradigm for improving the reasoning ability of large language models (LLMs). However, it faces two major challenges: test questions are often…
Tool learning has emerged as a crucial capability for large language models (LLMs) to solve complex real-world tasks through interaction with external tools. Existing approaches face significant challenges, including reliance on…
Recent advances in large reasoning models have been driven by reinforcement learning and test-time scaling, accompanied by growing interest in latent rather than purely textual reasoning. However, existing latent reasoning methods lack…
Reasoning is a fundamental capability of Large Language Models. While prior research predominantly focuses on enhancing narrow skills like math or code generation, improving performance on many other reasoning tasks remains challenging due…
While large language models (LLMs) have demonstrated remarkable reasoning capabilities, they often struggle with complex tasks that require specific thinking paradigms, such as divide-and-conquer and procedural deduction, \etc Previous…
Large Language Models (LLMs) have significantly advanced automated code generation, yet they struggle with complex coding tasks requiring multi-step logical reasoning. High-quality reasoning data is crucial for improving LLMs' reasoning…
Recently, large language models (LLMs) have shown remarkable reasoning capabilities via large-scale reinforcement learning (RL). However, leveraging the RL algorithm to empower effective multi-tool collaborative reasoning in LLMs remains an…
Thinking Tokens (TT) have been proposed as an unsupervised method to facilitate reasoning in language models. However, despite their conceptual appeal, our findings show that TTs marginally improves performance and consistently…
Length generalization, the ability to solve problems of longer sequences than those observed during training, poses a core challenge of Transformer-based large language models (LLM). Although existing studies have predominantly focused on…