UNIBROWSE：面向多模态 BrowseComp 的数据到智能体框架
论文提出 UNIBROWSE，一种将数据转化为智能体的框架，用于处理多模态 BrowseComp 任务。这类任务要求智能体在动态网页上融合感知、工具使用与长程推理，核心挑战包括组合结构、开放世界不确定性和多模态信息融合。该框架为开发者提供了新的数据到智能体方法，有望提升处理复杂网页智能体任务的能力。
独立 AI 资讯库
AI 前沿动态、原文归档与媒体镜像
从自动抓取数据库实时读取，适合快速浏览、检索和后续扩展成完整资讯站。
12005资讯
11873正文归档
75817媒体
Articulate Intuition or Genuine Analysis? Benchmarking Epistemic Reliability in LLM-as-a-Judge Peer Reviews
arXiv:2607.10511v1 Announce Type: new Abstract: When an LLM judge calls a peer review analytical and a human committee calls another review high quality, are they tracking the same thing? We argue they are not, and that the difference matters philosophically. We operationalise Kahneman's dual-proce
When Reasoning Hurts Legal Drafting: The Verbalization Bottleneck in Patent Claim Generation
arXiv:2607.10480v1 Announce Type: new Abstract: Patent claim drafting is a challenging legal drafting task that requires technical expertise, precise linguistic control, strict adherence to formal conventions, and the preservation of complex logical relationships among claim elements. While Chain-o
Enjoy Your Talk: A Human-Centered Benchmark for Multi-Turn Dialogue with Decoupled User Simulation, Target Modeling, and Judging
arXiv:2607.10428v1 Announce Type: new Abstract: Evaluating large language models (LLMs) as multi-turn conversational partners requires probing capabilities that single-turn benchmarks miss: persona consistency, evolving intent tracking, emotional dynamics, and goal completion. We introduce EYT-Benc
A Stepwise Questioning Expert-Editor Multi-Agent Framework for Long-Document Summarization
arXiv:2607.10390v1 Announce Type: new Abstract: Although large language models (LLMs) have shown promising potential in news summarization tasks, their performance on long-document summarization remains challenging as their length often exceeds the input limits. As the agent investment, which provi
Structured Thoughts For Improved Reasoning And Context Pruning
arXiv:2607.10386v1 Announce Type: new Abstract: Large language models (LLMs) excel at generating long chains of thought, but long reasoning traces are often verbose and memory-inefficient. In this work, we introduce Structured Thoughts, a framework that organizes reasoning into alternating and bl
CAFE: A Compound-AI Factorial Evaluation Framework
arXiv:2607.10380v1 Announce Type: new Abstract: We introduce CAFE (Compound-AI Factorial Evaluation), an open-source platform that brings design of experiments to the evaluation of compound AI systems (CAIS). Such systems expose many interchangeable choices - e.g. which retriever, model, or prompt
PolyInterview: An LLM-based Platform for Immersive Mock Interview Practice with Comprehensive Multimodal Assessment
arXiv:2607.10310v1 Announce Type: new Abstract: Preparing for job interviews is important for securing desired positions, yet realistic practice remains difficult to access: real interviews are infrequent, expert mock coaching is costly, and self-practice offers neither adaptive dialogue nor struct
PTEI: Integrating Personality Traits to Enhance Emotional Intelligence in Large Language Models
arXiv:2607.10245v1 Announce Type: new Abstract: Despite advances in Emotional Intelligence (EI), Large Language Models (LLMs) still significantly underperform humans in complex emotional reasoning. This gap originates partly from the limited incorporation of individual differences, particularly per
同等准确度，不平等的证据：搜索API作为工具使用型代理的决策界面
搜索API是许多AI代理的基础检索层，也是最常被调用的工具。传统搜索API返回URL、标题和网页内容片段，但整页检索消耗大量token，因此代理往往仅基于片段进行决策。本论文研究在搜索API作为决策界面的场景下，即使准确度相同，代理所能获得的证据也可能存在不均衡，这对工具使用型代理的设计与评估具有重要意义。
Cost of Reasoning in non-English Languages: A Case Study on Japanese
arXiv:2607.10114v1 Announce Type: new Abstract: Reasoning Language Models (RLMs) achieve their strongest performance when they reason in English, the language for which reasoning-oriented training data is most abundant. However, reasoning trace is a clue for model interpretability and safety, and u
Efficiently Adapting Spoken Language Models for the Singaporean Context
arXiv:2607.10092v1 Announce Type: new Abstract: Spoken language models (SLMs) unify speech perception and reasoning, but adapting them to sensitive domains is underexplored, especially when the original training data is inaccessible and the use case demands multilingual, spoken-query interaction. W
Robust, Scalable Detection of Text Containment in Large Web-Crawled Corpora
arXiv:2607.10020v1 Announce Type: new Abstract: We present FindMyText, an open-source Python package designed to efficiently assess whether a given text appears, in part or in full, within a text corpus. The tool builds on prior techniques for document fingerprinting, but extends them with a novel
Silent Failures in Quantized LLM Reasoning: A Taxonomy-Based Analysis of Hollow Convergence and Failure Mode Shifts
arXiv:2607.09999v1 Announce Type: new Abstract: We show that post-training quantization can silently alter how large language models reason even when task accuracy is preserved. Using a six-category failure taxonomy validated by two independent human annotators (Cohen's $\kappa$ = 0.906), we classi
Faithful by Design: Evaluating and Improving LLM-Generated Clinical Trial Summaries for Multi-Stakeholder Audiences
arXiv:2607.09932v1 Announce Type: new Abstract: Large language models are increasingly used to summarize clinical trial results for healthcare providers, patients, and payers, but their tendency to hallucinate poses significant risks in this high-stakes context. This study introduces a benchmark ev
Global Merger-Arbitrage Forecasting with Language Models
arXiv:2607.09921v1 Announce Type: new Abstract: We present a language-model forecasting system for merger arbitrage, a specialized high-stakes financial setting in which the task is to predict the outcome of announced M\&A deals. Unlike prior work on judgmental forecasting with LLMs, which has focu
RouteRec: Strict Evaluation of Recommender-Agent Selection and Aggregation
arXiv:2607.09908v1 Announce Type: new Abstract: Recommender systems increasingly face a choice among heterogeneous agents -- collaborative filters, sequential models, content-based retrievers, and LLM-based rerankers -- yet no single agent is uniformly best. We study this choice as task-aware agent
CLIR-Bench: Benchmarking Multimodal Question Answering over Irregular Clinical Time Series
arXiv:2607.09880v1 Announce Type: new Abstract: Clinical time series are central to patient monitoring, risk assessment, and clinical decision support. However, they are often sparse, irregularly sampled, and asynchronous, making it difficult for models to identify the temporal evidence required fo
Exploring Agentic Workflows for Generating High Quality Math Visual Aids
arXiv:2607.09839v1 Announce Type: new Abstract: Mathematical diagrams play a crucial role in K 12 education, both as problem components and as scaffolding for student comprehension. However, current AI tools, including Large Language Models (LLMs), struggle to reliably generate accurate and pedagog
基于自我发现规范的智能体上下文学习
上下文学习是一种新兴的推理时任务，要求大语言模型在没有预训练的情况下，从复杂语境中学习并应用新颖的任务特定知识；即使是前沿模型的任务成功率也不足24%。这项研究系统探讨了这一挑战，并提出了一种名为“自我发现规范”的智能体方法，引导模型自主挖掘任务约束。该方法将上下文学习从被动适应转变为主动规范发现，为开发者构建更强大的 AI 代理提供了新思路。
Semantic Drift and the Stability of Operator Control in Reasoning-Class Decision Support Systems
arXiv:2607.09790v1 Announce Type: new Abstract: The article investigates the fundamental problem of ensuring the stability of operator control and preserving goal-targeting in hybrid human-machine decision support systems (DSS) of a new generation. Based on a two-month continuous longitudinal exper
PHITSBench: an execution-scored benchmark for AI-assisted PHITS radiation-transport input generation using natural language
arXiv:2607.09789v1 Announce Type: new Abstract: We introduce PHITSBench, an execution-scored benchmark for the Monte Carlo Particle and Heavy Ion Transport code System (PHITS). PHITSBench comprises 282 transport-scorable tasks spanning three common workflow categories: parameter editing (Edit), syn
Length Penalties Make Chain-of-Thought Less Monitorable
arXiv:2607.09786v1 Announce Type: new Abstract: Length-penalized reinforcement learning can shorten chain-of-thought reasoning while hiding an influence that drives the model's answer. In our experiments, training with length penalties does not stop misleading hints from steering models, even thoug
EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents
arXiv:2607.09773v1 Announce Type: new Abstract: Computer-use agents must solve long-horizon tasks through repeated interaction with partially observable, multimodal desktop environments. Although imitation learning and offline trajectory refinement provide strong priors, static traces cannot cover
Verification of Adaptive Agentic Controllers through Finite Rule Revision
arXiv:2607.09770v1 Announce Type: new Abstract: Industrial agentic AI systems increasingly exhibit a gap between prototype capability and production deployment. In particular, adaptive agents may generate plausible outputs while remaining difficult to verify under non-determinism, confidentiality c
Norm Enforcement for AI Agents: Robustly Shaping Behavior in Multi-Agent Systems
arXiv:2607.09766v1 Announce Type: new Abstract: AI agents are increasingly deployed in shared environments where they pursue diverse goals and compete for rewards. This multi-agent competition can lead to behaviors that serve individual gains at collective cost -- for instance, marketing agents may
How Much Does Correctness Cost? Budgeted Placement of Strong Correctors in a Weak Multi-Agent Swarm
arXiv:2607.09765v1 Announce Type: new Abstract: A cheap swarm of unreliable agents can be steered to a correct consensus by a few strong, expensive "oracle" correctors. We ask how much one must spend, and where to place the oracles. We model the swarm as a consensus on a graph in which each oracle
BatteryLake: Agentic, Physics-Grounded Curation of Heterogeneous Battery Aging Data and Benchmarking
arXiv:2607.09762v1 Announce Type: new Abstract: Public battery aging datasets are a critical asset for advanced health management, but their practical use is often limited by inconsistent formats, unclear schemas, and metadata scattered across repositories and publications. Current curation remains
Replicating Belief, Not Bits: Epistemic State Replication for Agentic Systems
arXiv:2607.09748v1 Announce Type: new Abstract: In distributed systems, the classical State Machine Replication (SMR) model assumes that correct replicas execute deterministic transitions to yield identical bitwise states. However, the rise of agentic distributed systems -- where autonomous, stocha
SupplyNetPy: An Open-Source Python Library for High-Fidelity Modeling and Simulation of Arbitrary Supply Chain and Inventory Networks
arXiv:2607.09745v1 Announce Type: new Abstract: This paper introduces SupplyNetPy, an open-source, well-documented Python library for modeling and discrete-event simulation of supply chain networks with arbitrary multi-echelon structures. It supports multiple replenishment policies, perishable inve