Related papers: Understanding Tool-Integrated Reasoning
Recent Large Language Models (LLMs) have significantly advanced natural language processing and automated decision-making. However, these models still encounter difficulties when performing complex reasoning tasks involving logical…
Self-improvement training enables the large reasoning models (LRMs) to improve themselves by self-generating reasoning trajectories as training data without external supervision. However, we find that this method often falls short in…
Modern LLM reasoning relies on extensive test-time computation, driven by internal model training and external agentic orchestration. However, this synergy is often inefficient, as model verbosity and poor instruction following lead to…
With their high information density and intuitive readability, charts have become the de facto medium for data analysis and communication across disciplines. Recent multimodal large language models (MLLMs) have made notable progress in…
While reasoning models (e.g., DeepSeek R1) trained with reinforcement learning (RL), excel in textual reasoning, they struggle in scenarios requiring structured problem-solving, such as geometric reasoning, concise computation, or complex…
Tabular prediction traditionally relies on gradient-boosted decision trees and deep learning models, which excel in specific tasks but lack interpretability and transferability. Reasoning large language models (LLMs) promise cross-task…
Reasoning capabilities in large language models (LLMs) have generally advanced significantly. However, it is still challenging for existing reasoning-based LLMs to perform effective decision-making abilities in multi-agent environments, due…
Large language models (LLMs) increasingly rely on multi-turn tool-integrated planning for knowledge-intensive and complex reasoning tasks. Existing implementations typically rely on a single agent, but they suffer from limited context…
Multimodal Large Language Models (MLLMs) have achieved impressive performances in mathematical reasoning, yet they remain vulnerable to visual hallucinations and logical inconsistencies that standard outcome-based supervision fails to…
Chain-of-Thought (CoT) reasoning enhances Large Language Models (LLMs) by prompting intermediate steps, improving accuracy and robustness in arithmetic, logic, and commonsense tasks. However, this benefit comes with high computational…
Tool-Integrated Reasoning has emerged as a key paradigm to augment Large Language Models (LLMs) with computational capabilities, yet integrating tool-use into long Chain-of-Thought (long CoT) remains underexplored, largely due to the…
Vision-language models with extended reasoning succeed on complex problems, but many real-world problems require external tools that internal reasoning alone often cannot resolve. Agentic reasoning therefore interleaves two behaviors with a…
Theory of Mind (ToM) assesses whether models can infer hidden mental states such as beliefs, desires, and intentions, which is essential for natural social interaction. Although recent progress in Large Reasoning Models (LRMs) has boosted…
While large language models (LLMs) have demonstrated remarkable reasoning capabilities, they are not without their flaws and inaccuracies. Recent studies have introduced various methods to mitigate these limitations. Temporal reasoning…
Tool-augmented large language models (LLMs) are attracting widespread attention when accessing up-to-date knowledge and alleviating hallucination issues. Nowadays, advanced closed-source LLMs (e.g., ChatGPT) have demonstrated surprising…
Enhancing reasoning capabilities remains a central focus in the LLM reasearch community. A promising direction involves requiring models to simulate code execution step-by-step to derive outputs for given inputs. However, as code is often…
Large Language Models (LLMs) have been used to make decisions in complex scenarios, where they need models to think deeply, reason logically, and decide wisely. Many existing studies focus solely on multi-round conversations in social tasks…
Reasoning-oriented Large Language Models (LLMs) have achieved remarkable progress with Chain-of-Thought (CoT) prompting, yet they remain fundamentally limited by a \emph{blind self-thinking} paradigm: performing extensive internal reasoning…
Recent advances in large language models (LLMs) have demonstrated remarkable reasoning capabilities, largely stimulated by Reinforcement Learning with Verifiable Rewards (RLVR). However, existing RL algorithms face a fundamental limitation:…
Recent advancements in Large Language Models (LLMs) have shifted from explicit Chain-of-Thought (CoT) reasoning to more efficient latent reasoning, where intermediate thoughts are represented as vectors rather than text. However, latent…