Related papers: Plan Before Search: Search Agents Need Plan

Molecular property prediction and generative design via deep learning models has been the subject of intense research given its potential to accelerate development of new, high-performance materials. More recently, these workflows have been…

Existing research on large language models (LLMs) shows that they can solve information extraction tasks through multi-step planning. However, their extraction behavior on complex sentences and tasks is unstable, emerging issues such as…

Large language models (LLMs) have notably progressed in multi-step and long-chain reasoning. However, extending their reasoning capabilities to encompass deep interactions with search remains a non-trivial challenge, as models often fail to…

Agentic RAG is a powerful technique for incorporating external information that LLMs lack, enabling better problem solving and question answering. However, suboptimal search behaviors exist widely, such as over-search (retrieving…

Retrieval-Augmented Generation (RAG) effectively enhances Large Language Models (LLMs) by incorporating retrieved external knowledge into the generation process. Reasoning models improve LLM performance in multi-hop QA tasks, which require…

Large Language Models (LLMs) have shown remarkable advancements in tackling agent-oriented tasks. Despite their potential, existing work faces challenges when deploying LLMs in agent-based environments. The widely adopted agent paradigm…

The field of reinforcement learning (RL) is facing increasingly challenging domains with combinatorial complexity. For an RL agent to address these challenges, it is essential that it can plan effectively. Prior work has typically utilized…

Large Language Model agents excel at solving complex tasks through iterative reasoning and tool use, but typically depend on ultra-large, costly backbones. Existing distillation approaches train smaller students to imitate full teacher…

Pretraining Large Language Models (LLMs) on large corpora of textual data is now a standard paradigm. When using these LLMs for many downstream applications, it is common to additionally bake in new knowledge (e.g., time-critical news, or…

Large Language Models (LLMs) have shown impressive capabilities in multi-step reasoning and problem-solving.Recent works introduce multi-agent reflection frameworks where multiple LLM agents critique and refine each other's outputs using…

We investigate the ability of language models to perform compositional reasoning tasks where the overall solution depends on correctly composing the answers to sub-problems. We measure how often models can correctly answer all sub-problems…

Capability distillation applies knowledge distillation to selected model capabilities, aiming to compress a large language model (LLM) into a smaller one while preserving the abilities needed for a downstream task. However, most existing…

Large reasoning models such as DeepSeek-R1 and their distilled variants achieve strong performance on complex reasoning tasks. Yet, distilling these models often demands large-scale data for supervised fine-tuning (SFT), motivating the…

A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environments that approach the vastness and scale of the real world,…

Building a search relevance model that achieves both low latency and high performance is a long-standing challenge in the search industry. To satisfy the millisecond-level response requirements of online systems while retaining the…

Large Language Models (LLMs) have exhibited remarkable capabilities in many complex tasks including mathematical reasoning. However, traditional approaches heavily rely on ensuring self-consistency within single prompting method, which…

In this paper, we propose a novel factored agent architecture designed to overcome the limitations of traditional single-agent systems in agentic AI. Our approach decomposes the agent into two specialized components: (1) a large language…

Reward modeling is essential for aligning large language models with human preferences through reinforcement learning. To provide accurate reward signals, a reward model (RM) should stimulate deep thinking and conduct interpretable…

The prevailing paradigm for training large reasoning models--combining Supervised Fine-Tuning (SFT) with Reinforcement Learning with Verifiable Rewards (RLVR)--is fundamentally constrained by its reliance on high-quality, human-annotated…

Answering multi-hop reasoning questions requires retrieving and synthesizing information from diverse sources. Language models (LMs) struggle to perform such reasoning consistently. We propose an approach to pinpoint and rectify multi-hop…