Related papers: HyPER: Bridging Exploration and Exploitation for S…

Reinforcement learning (RL) is emerging as a powerful paradigm for enabling large language models (LLMs) to perform complex reasoning tasks. Recent advances indicate that integrating RL with retrieval-augmented generation (RAG) allows LLMs…

Reading Comprehension has received significant attention in recent years as high quality Question Answering (QA) datasets have become available. Despite state-of-the-art methods achieving strong overall accuracy, Multi-Hop (MH) reasoning…

Efficient multi-hop reasoning requires Large Language Models (LLMs) based agents to acquire high-value external knowledge iteratively. Previous work has explored reinforcement learning (RL) to train LLMs to perform search-based document…

Large Language Models (LLMs) are demonstrating rapid improvements on complex reasoning benchmarks, particularly when allowed to utilize intermediate reasoning steps before converging on a final solution. However, current literature often…

Sequential decision tasks with incomplete information are characterized by the exploration problem; namely the trade-off between further exploration for learning more about the environment and immediate exploitation of the accrued…

Parallel thinking has emerged as a new paradigm for large reasoning models (LRMs) in tackling complex problems. Recent methods leverage Reinforcement Learning (RL) to enhance parallel thinking, aiming to address the limitations in…

Inference-time scaling techniques have shown promise in enhancing the reasoning capabilities of large language models (LLMs). While recent research has primarily focused on training-time optimization, our work highlights inference-time…

Scaling large language models (LLMs) has driven significant advancements, yet it faces diminishing returns and escalating energy demands. This work explores how test-time compute (TTC) can serve as an energy-efficient complement to…

Reinforcement learning with verifiable rewards, particularly Group Relative Policy Optimization (GRPO), has significantly advanced the reasoning capabilities of Large Language Models (LLMs). However, in complex tasks, GRPO frequently…

Enhancing the reasoning capabilities of large language models (LLMs), particularly for complex tasks requiring multi-step logical deductions, remains a significant challenge. Traditional inference time scaling methods utilize scalar reward…

Model checking has been successfully used in many computer science fields, including artificial intelligence, theoretical computer science, and databases. Most of the proposed solutions make use of classical, point-based temporal logics,…

Reasoning language models have shown an uncanny ability to improve performance at test-time by ``thinking longer''-that is, by generating longer chain-of-thought sequences and hence using more compute. However, the length of their…

Answering complex real-world questions requires step-by-step retrieval and integration of relevant information to generate well-grounded responses. However, existing knowledge distillation methods overlook the need for different reasoning…

Tasks on complex systems require high-precision numerical computation to support decisions, but current large language models (LLMs) cannot integrate such computations as an intrinsic and interpretable capability with existing…

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…

While Large Language Models (LLMs) excel at reasoning on text and Vision-Language Models (VLMs) are highly effective for visual perception, applying those models for visual instruction-based planning remains a widely open problem. In this…

Large language models increasingly rely on either reinforcement learning or multi-agent prompting to improve reasoning, yet these two paradigms remain difficult to combine. Directly applying single-agent reinforcement learning to multi-turn…

Large Language Models (LLMs) increasingly rely on multi-turn reasoning and interaction, such as adaptive retrieval-augmented generation (RAG) and ReAct-style agents, to answer difficult questions. These methods improve accuracy by…

Recent advancements in aligning large language models via reinforcement learning have achieved remarkable gains in solving complex reasoning problems, but at the cost of expensive on-policy rollouts and limited exploration of diverse…

Reasoning-augmented search agents, such as Search-R1, are trained to reason, search, and generate the final answer iteratively. Nevertheless, due to their limited capabilities in reasoning and search, their performance on multi-hop QA…