Related papers: Coordinating Search-Informed Reasoning and Reasoni…

In this work, we focus on the problem of retrieving relevant arguments for a query claim covering diverse aspects. State-of-the-art methods rely on explicit mappings between claims and premises, and thus are unable to utilize large…

Tree search has become as a representative framework for test-time reasoning with large language models (LLMs), exemplified by methods such as Tree-of-Thought and Monte Carlo Tree Search. However, it remains difficult to provide instant and…

Given the volume of potentially false claims online, claim prioritization is essential in allocating limited human resources available for fact-checking. In this study, we perceive claim prioritization as an information retrieval (IR) task:…

The use of skills (a.k.a., options) can greatly accelerate exploration in reinforcement learning, especially when only sparse reward signals are available. While option discovery methods have been proposed for individual agents, in…

Existing RAG benchmarks often overlook query difficulty, leading to inflated performance on simpler questions and unreliable evaluations. A robust benchmark dataset must satisfy three key criteria: quality, diversity, and difficulty, which…

Determining whether a given claim is supported by evidence is a fundamental NLP problem that is best modeled as Textual Entailment. However, given a large collection of text, finding evidence that could support or refute a given claim is a…

With recent advancements in large language models, methods like chain-of-thought prompting to elicit reasoning chains have been shown to improve results on reasoning tasks. However, tasks that require multiple steps of reasoning still pose…

Intelligent physical systems as embodied cognitive systems must perform high-level reasoning while concurrently managing an underlying control architecture. The link between cognition and control must manage the problem of converting…

According to cognitive psychology and related disciplines, the development of complex problem-solving behaviour in biological agents depends on hierarchical cognitive mechanisms. Hierarchical reinforcement learning is a promising…

Large language model (LLM)-based search agents have proven promising for addressing knowledge-intensive problems by incorporating information retrieval capabilities. Existing works largely focus on optimizing the reasoning paradigms of…

Agentic retrieval-augmented generation (RAG) formulates question answering as a multi-step interaction between reasoning and information retrieval, and has recently been advanced by reinforcement learning (RL) with outcome-based…

Designing a generalist scientific agent capable of performing tasks in laboratory settings to assist researchers has become a key goal in recent Artificial Intelligence (AI) research. Unlike everyday tasks, scientific tasks are inherently…

Agentic retrieval improves multi-hop question answering by giving language models autonomy to iteratively gather evidence. Recent work augments these systems with knowledge graphs for structured traversal, but this combination introduces…

Current AI-powered research systems adopt a direct search-then-summarize paradigm that treats hypotheses as end products of scientific discovery. We argue this leaves a critical gap: hypotheses can serve a far more powerful role as…

Drawing meaningful conclusions from inherently multimodal clinical data (including medical imaging) requires coordinating expertise across the clinical specialty, radiology, programming, and biostatistics. This fragmented process…

Reinforcement learning (RL) has become an effective approach for advancing the reasoning capabilities of large language models (LLMs) through the strategic integration of external search engines. However, current RL-based search agents…

Real-world multi-hop QA is naturally linked with ambiguity, where a single query can trigger multiple reasoning paths that require independent resolution. Since ambiguity can occur at any stage, models must navigate layered uncertainty…

Curriculum learning helps language models tackle complex reasoning by gradually increasing task difficulty. However, it often fails to generate consistent step-by-step reasoning, especially in multilingual and low-resource settings where…

Agentic search enables language models to solve knowledge-intensive tasks by adaptively acquiring external evidence over multiple steps. Reinforcement learning with verifiable rewards (RLVR) has emerged as a widely adopted training paradigm…

Motivated by the underspecified, multi-hop nature of search queries and the multimodal, heterogeneous, and often conflicting nature of real-world web results, we introduce MERRIN (Multimodal Evidence Retrieval and Reasoning in Noisy Web…