The paper introduces VibeSearchBench, a new benchmark designed to evaluate long-horizon, proactive search capabilities, demonstrating that current state-of-the-art LLM agents are still significantly i…

The paper introduces K-BrowseComp, a new web-browsing agent benchmark of 400 problems grounded in Korean contexts, demonstrating that current frontier LLMs struggle significantly with complex, context…

The paper introduces ForeSci, a novel benchmark that evaluates LLM agents' ability to make forward-looking research judgments using only historical evidence, finding that explicit evidence organizatio…

The paper introduces the concept of Search-Time Contamination (STC), demonstrating that deep research agents can leak information from public benchmarks via web search, leading to an overestimation of…

The paper presents SearchLog, a web browser extension for collecting natural search logs during lab-based studies.

MEMENTO proposes a novel framework that treats the open web as a continuous learning signal, enabling agents to acquire task-specific expertise and reusable research strategies in low-data domains wit…

The paper introduces ProjectionBench, a novel benchmark that progressively discloses information to evaluate LLMs' ability to generate scientific hypotheses, demonstrating that advanced models like GP…

The paper introduces a Deep Research pipeline that significantly improves literature search recall and demonstrates that human-curated citation lists are often unreliable and do not serve as a true gr…

The paper proposes MERIT, a dual-level, multi-horizon memory retrieval framework that significantly improves the performance of interactive text-to-SQL agents by providing both global and local memory…

The paper introduces AGENTCL, a rigorous evaluation framework that uses controlled task streams to accurately measure an agent's ability to accumulate and reuse knowledge across multiple tasks, thereb…

Despite having access to web search, users' reliance on conversational AI for information remains high, driven primarily by pre-existing trust and influenced indirectly by the chatbot's conversational…

The paper introduces Plan, a structured agentic behavior that decomposes multi-hop questions into ordered sub-questions before retrieval, and proposes a self-bootstrapping paradigm to train it without…

This paper introduces cost-aware Retrieval-Augmented Generation (RAG), demonstrating that fixed evidence selection is brittle and that adaptive, agentic controllers are necessary for effective knowled…

Critic-R introduces a novel framework that uses a critic model to provide natural language introspective feedback, significantly improving the performance of agentic search systems by optimizing retri…

This paper analyzes failure modes in collaborative visual reasoning systems, demonstrating that naive shared workspaces can amplify hallucinations and proposing diagnostics for improving communication…

The study compares agentic data retrieval using unstructured web data versus structured, semantically-annotated datasets, concluding that semantic metadata remains essential for high-precision, reliab…

The paper introduces CITETRACE, a large-scale dataset and evaluation framework that systematically measures structural citation failures in search-augmented LLMs, revealing a pattern called Verified M…

The paper introduces Harness-1, a search agent that separates semantic decision-making from state management by using a stateful search harness, achieving state-of-the-art performance across diverse r…

GrepSeek introduces a novel direct corpus interaction (DCI) search agent that trains an LLM to find and compose evidence from large text corpora by issuing executable shell commands, achieving state-o…

This paper evaluates the performance of a Large Language Model (LLM) in a high-stakes context by comparing it to human experts and measuring variance and error magnitude.