Related papers: Beyond Turn Limits: Training Deep Search Agents wi…
Long-form chain-of-thought reasoning has become a cornerstone of advanced reasoning in large language models. While recent verification-refinement frameworks have enabled proprietary models to solve Olympiad-level problems, their…
Medical reasoning models remain constrained by parametric knowledge and are thus susceptible to forgetting and hallucinations. DeepResearch (DR) models ground outputs in verifiable evidence from tools and perform strongly in general…
The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success…
Search-integrated reasoning enables language agents to transcend static parametric knowledge by actively querying external sources. However, training these agents via reinforcement learning is hindered by the multi-scale credit assignment…
With the continuous advancement of Large Language Models (LLMs), intelligent agents are becoming increasingly vital. However, these agents often fail in environments governed by implicit rules--hidden constraints that cannot be observed…
Recent advancements in multimodal reward models (RMs) have substantially improved post-training for visual generative models. However, current RMs face inherent limitations: (1) visual inputs consume large context budgets, forcing fewer…
Research on applications of reinforcement learning (RL) to large language models has mostly been focused on single-turn problems, such as mathematical reasoning or single-shot code generation. While these problems can be viewed as…
Current Large Language Models (LLMs) face inherent limitations due to their pre-defined context lengths, which impede their capacity for multi-hop reasoning within extensive textual contexts. While existing techniques like…
Large Language Model (LLM)-based agents demonstrate advanced reasoning capabilities, yet practical constraints frequently limit outputs to single responses, leaving significant performance potential unrealized. This paper introduces MARINE…
Multimodal Large Language Models (MLLMs) based agents have demonstrated remarkable potential in autonomous web navigation. However, handling long-horizon tasks remains a critical bottleneck. Prevailing strategies often rely heavily on…
Recent progress in reasoning with large language models (LLMs), such as DeepSeek-R1, demonstrates impressive capabilities in domains like mathematics and coding, by exhibiting complex cognitive behaviors such as verification, goal…
Web-based 'deep research' agents aim to solve complex question - answering tasks through long-horizon interactions with online tools. These tasks remain challenging, as the underlying language models are often not optimized for long-horizon…
Effective conversational search demands a deep understanding of user intent across multiple dialogue turns. Users frequently use abbreviations and shift topics in the middle of conversations, posing challenges for conventional retrievers.…
Embedding models play a pivot role in modern NLP applications such as IR and RAG. While the context limit of LLMs has been pushed beyond 1 million tokens, embedding models are still confined to a narrow context window not exceeding 8k…
Existing multimodal retrieval systems excel at semantic matching but implicitly assume that query-image relevance can be measured in isolation. This paradigm overlooks the rich dependencies inherent in realistic visual streams, where…
Reasoning models have recently shown remarkable progress in domains such as math and coding. However, their expert-level abilities in math and coding contrast sharply with their performance in long-horizon, interactive tasks such as web…
Building on the success of text-based reasoning models like DeepSeek-R1, extending these capabilities to multimodal reasoning holds great promise. While recent works have attempted to adapt DeepSeek-R1-style reinforcement learning (RL)…
Agent-compiled knowledge bases provide persistent external knowledge for large language model (LLM) agents in open-ended, knowledge-intensive downstream tasks. Yet their quality is systematically limited by \emph{incompleteness},…
Deep-research agents are capable of executing multi-step web exploration, targeted retrieval, and sophisticated question answering. Despite their powerful capabilities, deep-research agents face two critical bottlenecks: (1) the lack of…
Large language models face challenges in long-context question answering, where key evidence of a query may be dispersed across millions of tokens. Existing works equip large language models with a memory buffer that is dynamically updated…