Related papers: ARS: Adaptive Reasoning Suppression for Efficient …
This paper explores the system 1 thinking capability of Large Reasoning Models (LRMs), the intuitive ability to respond efficiently with minimal token usage. While existing LRMs rely on long-chain reasoning and excel at complex tasks, their…
Large language models (LLMs) have exhibited extraordinary performance in a variety of tasks while it remains challenging for them to solve complex multi-step tasks as agents. In practice, agents sensitive to the outcome of certain key steps…
Large language models (LLMs) excel at mathematical reasoning and logical problem-solving. The current popular training paradigms primarily use supervised fine-tuning (SFT) and reinforcement learning (RL) to enhance the models' reasoning…
A popular approach for improving the correctness of output from large language models (LLMs) is Self-Consistency - poll the LLM multiple times and output the most frequent solution. Existing Self-Consistency techniques always generate a…
Recent studies have shown that large language models (LLMs), especially smaller ones, often lack robustness in grade school math (GSM) reasoning. In particular, they tend to experience performance drops when faced with distribution shifts,…
Large Language Models (LLMs) are increasingly relied upon for solving complex reasoning tasks in domains such as mathematics, logic, and multi-step question answering. A growing line of work seeks to improve reasoning quality by scaling…
Structured representations, exemplified by Abstract Meaning Representation (AMR), have long been pivotal in computational linguistics. However, their role remains ambiguous in the Large Language Models (LLMs) era. Initial attempts to…
Aligning general-purpose large language models (LLMs) to downstream tasks often incurs significant training adjustment costs. Prior research has explored various avenues to enhance alignment efficiency, primarily through minimal-data…
With the advent of large language models (LLMs), there has been a great deal of interest in applying them to solve difficult programming tasks. Recent work has demonstrated their potential at program optimization, a key challenge in…
Reinforcement learning with verifiable rewards (RLVR) has been shown to enhance the reasoning capabilities of large language models (LLMs), enabling the development of large reasoning models (LRMs). However, LRMs such as DeepSeek-R1 and…
Large Audio Language Models (LALMs), powered by the chain-of-thought (CoT) paradigm, have shown remarkable reasoning capabilities. Intuitively, different problems often require varying depths of reasoning. While some methods can determine…
Service composition remains a central challenge in building adaptive and intelligent software systems, often constrained by limited reasoning capabilities or brittle execution mechanisms. This paper explores the integration of two emerging…
Recent breakthroughs in Large Language Models (LLMs) have led to the emergence of agentic AI systems that extend beyond the capabilities of standalone models. By empowering LLMs to perceive external environments, integrate multimodal…
Explicit chain-of-thought (CoT) reasoning substantially improves the reasoning ability of large language models (LLMs), but incurs high inference cost due to lengthy autoregressive traces. Existing latent reasoning methods offer a promising…
The remarkable success of Large Language Models (LLMs) relies heavily on their substantial scale, which poses significant challenges during model deployment in terms of latency and memory consumption. Recently, numerous studies have…
While recent success of large reasoning models (LRMs) significantly advanced LLMs' reasoning capability by optimizing the final answer accuracy using reinforcement learning, they may also drastically increase the output length due to…
The demand for efficient large language model (LLM) inference has propelled the development of dedicated accelerators. As accelerators are vulnerable to hardware faults due to aging, variation, etc, existing accelerator designs often…
Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external knowledge but incurs significant inference costs due to lengthy retrieved contexts. While context compression mitigates this issue, existing methods…
Self-Taught Reasoners (STaR), synonymously known as Rejection sampling Fine-Tuning (RFT), is an integral part of the training pipeline of self-improving reasoning Language Models (LMs). The self-improving mechanism often employs random…
Large Reasoning Models (LRMs) have demonstrated remarkable capabilities by scaling up the length of Chain-of-Thought (CoT). However, excessively long reasoning traces pose substantial challenges for training cost and inference latency.…