Sarim Hashmi, Mukul Ranjan, Kshitij Mishra, Mikhail Kuznetsov, Praneeth Vepakomma, Nils Lukas · Oct 6, 2026 · Citations: 0
Simulation EnvGeneral
Web agents complete user requests by reading and acting on pages that third parties write, so an instruction planted on a page can redirect the agent away from the user's goal.
We introduce AdvSim2Real, which co-evolves a task curriculum, an injection adversary, and the agent inside a frozen web world model.
We treat it as a family of measurable scaling relations: for each risk category r, the alignment burden needed to hold a fixed safety target is modeled as B_r(N)=a_rN^alpha_r, with N a capability proxy; against a budget proportional to N,…
A preregistered pilot on Qwen2.5 0.5B-72B finds exponents of -0.05 for truthfulness and 0.48 for stated dispositions (both scaling helps under its reduced rule, though local slopes approach 1 at the top; replicated on Qwen3 0.6B-14B), while…
Yifan Zhang, Yutong Dai, Viraj Prabhu, Zhiyuan Hu, Ran Xu, Zeyuan Chen · Oct 5, 2026 · Citations: 0
Simulation EnvGeneral
Open-source web agents are now strong enough to execute realistic browser tasks, but training them with reinforcement learning still depends on weak supervision: binary task success is too sparse for credit assignment, while…
During training, the agent answers natural-language verification questions about its own rollouts; a Compositional Conformal Certifier keeps only question signals whose URL-conditional evidence agrees with a training-time judge, assigns…
Soyeong Jeong, Sujay Kumar Jauhar, Sung Ju Hwang, Andrew Joohun Nam · Sep 29, 2026 · Citations: 0
General
Recent LLM agents approach this by iteratively searching the full corpus rather than reading only a fixed set of top-ranked documents.
Using 7 different models with 3 benchmark datasets, we show that CorpusMap improves both evidence discovery and answer quality over raw-corpus agentic search while using fewer tokens on average, and further outperforms 4 alternative…
Jiajun Wu, Jian Yang, Yaxin Du, Wei Zhang, Haowen Wang, Junhang Cheng · Aug 31, 2026 · Citations: 0
Critique EditSimulation EnvLawCoding
VLM-driven self-improvement of web code has a structural flaw: the model that proposes the repair is the model that judges it, and visual plausibility under that judge is a poor proxy for whether the page actually works.
Zhuochun Li, Youngmin Ko, Ali Keramati, Tuhin Kundu, Liang-Chun Tsai, Nicola Ferri · Aug 20, 2026 · Citations: 0
Automatic MetricsCoding
Recent agent benchmarks increasingly ground evaluation in executable environments, from code repair to web navigation, app APIs, and function calling.
In this paper, we introduce Thinkingbox, a sandbox for tool-agent-user interaction that provides isolated MCP-compatible tool sessions, complete execution traces, and outcome evaluation over terminal backend state.
In this paper, we propose RAVEN, an agentic memory system for long-horizon robotic question answering and navigation.
Across several simulated and real-world video question-answering benchmarks, RAVEN consistently surpasses caption-based memory systems and matches frontier VLMs on long-horizon tasks at 10\times lower retrieval cost.
Annika Marie Schoene, Cansu Canca, Gautham Vijay Kumar, Anson Antony · Jun 22, 2026 · Citations: 0
Medicine
General-purpose large language models (LLMs) are increasingly used for mental health-related conversations, yet safety guardrails remain inadequate and inconsistent across clinical conditions.
This study evaluates eight proprietary LLMs across 16 DSM-5 conditions using four adversarial attack variants, introducing an eight-dimension harm taxonomy and a multi-dimensional evaluation framework.
To Eun Kim, Xuhong He, Dishank Jain, Ambuj Agrawal, Negar Arabzadeh, Fernando Diaz · Jun 18, 2026 · Citations: 0
Simulation EnvGeneral
The decentralized deployment of LLM agents with diverse capabilities across diverse tasks motivates infrastructure for knowledge sharing across heterogeneous agent populations.
We propose Multi-Agent Transactive Memory (MATM), a framework for population-level storage and retrieval of agent-generated trajectories, where producer agents contribute trajectories to a shared repository and consumer agents retrieve them…
Ben Torkian, Jun Zhou · Jun 11, 2026 · Citations: 0
Medicine
We present a Safety-First Science Gateway for maternal and child health (MCH) resource navigation that combines large language models (LLMs) and retrieval-augmented generation (RAG) with a multi-layer safety architecture.
The current system provides resource provenance and safety-bounded navigation; it does not constitute a clinical decision-support system or automated claim-by-claim verification of generated health information.
Yating Pan, Jiajun Zhang, Jun Wang, Qi Su · May 29, 2026 · Citations: 0
Coding
LLM-based research agents have advanced rapidly in science and engineering, where research is organized around executable experiments, code, and quantitative signals.
To address this gap, we introduce SPIRE (Scholarly-Primitives-Inspired Research Engine), a multi-agent framework that realizes Scholarly Primitives, a typology of basic humanities scholarship practices, as cooperating roles over a…
Qiuyue Wang, Mingsheng Li, Jian Guan, Jinhui Ye, Sicheng Xie, Yitao Liu · May 28, 2026 · Citations: 0
DemonstrationsSimulation EnvGeneral
Qwen-VLA is trained with a large-scale joint pretraining recipe over diverse data sources, including robotics manipulation trajectories, human egocentric demonstrations, synthetic simulation data, vision-and-language navigation data,…
Experiments on manipulation, navigation, and trajectory-centric benchmarks show consistent multi-task performance and out-of-distribution generalization under variations in scene layout, background, lighting, object configuration, and robot…
Amin Karimi Monsefi, Dominic Culver, Nikhil Bhendawade, Manuel R. Ciosici, Yizhe Zhang, Irina Belousova · May 8, 2026 · Citations: 0
Automatic MetricsGeneral
Each training trajectory is built through a chain of blind stochastic jumps with no evaluation of sequence quality; a single bad decision at an early midpoint propagates through subsequent steps, yet the student must imitate the result.
We demonstrate the system's effectiveness through comprehensive evaluation across multiple extraction scenarios in Traditional Chinese Medicine research, achieving structured output compliance rates exceeding 94\% and information extraction…
Haozhan Tang, Xiuqi Zhu, Xinyin Zhang, Boxun Li, Virginia Smith, Kevin Kuo · May 8, 2026 · Citations: 0
MedicineCoding
Through empirical evaluation across diverse tasks (SQL, Medical QA, and Counterfactual Knowledge) and varying language models (Gemma-3-1B, Qwen2.5-1.5B, and Qwen2.5-3B), we verify both trends and demonstrate that relying solely on either…
Our evaluations show that MoLF either improves on or stays within 1.5\% of the better of FFT and LoRA across all settings, while MoLF-Efficient outperforms prior adaptive LoRA approaches by up to 20\% on Fact and 9\% on Med and SQL.
