Related papers: ReThinker: Scientific Reasoning by Rethinking with…
Large Language Models exhibit impressive reasoning capabilities across diverse tasks, motivating efforts to distill these capabilities into smaller models through generated reasoning data. However, direct training on such synthesized…
Large Language Models (LLMs) have revolutionized recommendation agents by providing superior reasoning and flexible decision-making capabilities. However, existing methods mainly follow a passive information acquisition paradigm, where…
Large language models (LLMs) have recently shown strong progress on scientific reasoning, yet two major bottlenecks remain. First, explicit retrieval fragments reasoning, imposing a hidden "tool tax" of extra tokens and steps. Second,…
Reverse thinking plays a crucial role in human reasoning. Humans can reason not only from a problem to a solution but also in reverse, i.e., start from the solution and reason towards the problem. This often enhances overall reasoning…
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…
Language models (LMs) have recently shown remarkable performance on reasoning tasks by explicitly generating intermediate inferences, e.g., chain-of-thought prompting. However, these intermediate inference steps may be inappropriate…
Large language models (LLMs) have shown remarkable performance in complex reasoning tasks, but their efficiency is hindered by the substantial memory and computational costs associated with generating lengthy tokens. In this paper, we…
Large language models (LLMs) have achieved strong performance on complex reasoning tasks using techniques such as chain-of-thought and self-consistency. However, ensemble-based approaches, especially self-consistency which relies on…
Large Language Models (LLMs) have emerged as powerful tools for generating coherent text, understanding context, and performing reasoning tasks. However, they struggle with temporal reasoning, which requires processing time-related…
Instruction-based image editing has emerged as a prominent research area, which, benefiting from image generation foundation models, have achieved high aesthetic quality, making instruction-following capability the primary challenge.…
Recent advancements in large language models, multimodal large language models, and large audio language models (LALMs) have significantly improved their reasoning capabilities through reinforcement learning with rule-based rewards.…
With large language models (LLMs) increasingly deployed as cognitive engines for AI agents, the reliability and effectiveness critically hinge on their intrinsic epistemic agency, which remains understudied. Epistemic agency, the ability to…
Large reasoning models (LRMs) have exhibited remarkable reasoning capabilities through inference-time scaling, but this progress has also introduced considerable redundancy and inefficiency into their reasoning processes, resulting in…
Large language models have advanced rapidly, from pattern recognition to emerging forms of reasoning, yet they remain confined to linguistic simulation rather than grounded understanding. They can produce fluent outputs that resemble…
Large Reasoning Models (LRMs) have shown remarkable reasoning capabilities, yet they often suffer from overthinking, expending redundant computational steps on simple problems, or underthinking, failing to explore sufficient reasoning paths…
Retrosynthetic planning is a fundamental task in organic chemistry, yet remains challenging due to its combinatorial complexity. To address this, conventional approaches typically rely on hybrid frameworks that combine single-step…
Reinforcement learning with verifiable rewards improves language model reasoning, but its reliance on domain-specific verifiers, sparse outcome rewards, and coarse-grained credit assignment limits its applicability. We introduce…
Deep research agents increasingly automate complex information-seeking tasks, producing evidence-grounded reports via multi-step reasoning, tool use, and synthesis. Their growing role demands scalable, reliable evaluation, positioning…
Large language models (LLMs) with Chain-of-Thought (CoT) reasoning have achieved strong performance across diverse tasks, including mathematics, coding, and general reasoning. A distinctive ability of these reasoning models is…
Existing prompt-optimization techniques rely on local signals to update behavior, often neglecting broader and recurring patterns across tasks, leading to poor generalization; they further rely on full-prompt rewrites or unstructured…