Multimodal web agents that process both screenshots and accessibility trees are increasingly deployed to interact with web interfaces, yet their dual-stream architecture opens an underexplored attack surface: an adversary who injects…
Motivated by this finding, we propose Dual-Modality Multi-Stage Adversarial Safety Training (DMAST), a framework that formalizes the agent-attacker interaction as a two-player general-sum Markov game and co-trains both players through a…
On code generation (LiveCodeBench, CodeContests, SWE-Bench) and math reasoning (AIME, HMMT) benchmarks, V_1-Infer improves Pass@1 by up to 10% over pointwise verification and outperforms recent test-time scaling methods while being…
Psychiatric consultation requires agents to elicit discriminative evidence, map uncertain narratives to diagnostic criteria, and decide when evidence suffices.
Nicholas Kluge Corrêa, Aniket Sen, Shiza Fatimah, Sophia Falk, Lennard Landgraf, Julia Kastner · Mar 3, 2026 · Citations: 0
Pairwise PreferenceCoding
Following our previous works, we now extend our dataset, GigaVerbo-v2, to a new degree of quality and scale, while also introducing a new synthetic dataset, GigaVerbo-v2 Synth, aimed at filling missing gaps in GigaVerbo-v2, and two…
Through extensive ablation studies, we design both pretraining and continual pretraining recipes for the Tucano 2 suite (Base, Instruct, and Think), which achieve state-of-the-art performance on several Portuguese-language modeling…
To avoid costly clinician labeling, we introduce an annotation-free preference construction strategy that pairs physician responses with filtered non-expert generations.
We evaluate PrivMedChat across medical dialogue tasks and assess utility, safety, and privacy under consistent privacy accounting, thereby providing a practical pathway to align medical chatbots while offering formal privacy guarantees.
To address the challenge, in this work, we propose StitchCUDA, a multi-agent framework for end-to-end GPU program generation, with three specialized agents: a Planner to orchestrate whole system design, a Coder dedicated to implementing it…
Experiments on KernelBench show that StitchCUDA achieves nearly 100% success rate on end-to-end GPU programming tasks, with 1.72x better speedup over the multi-agent baseline and 2.73x than the RL model baselines.
Minseok Choi, Dongjin Kim, Seungbin Yang, Subin Kim, Youngjun Kwak, Juyoung Oh · Mar 3, 2026 · Citations: 0
Expert VerificationLawMedicine
With the growing deployment of large language models (LLMs) in real-world applications, establishing robust safety guardrails to moderate their inputs and outputs has become essential to ensure adherence to safety policies.
Comprehensive evaluations conducted on ExpGuardTest and eight established public benchmarks reveal that ExpGuard delivers competitive performance across the board while demonstrating exceptional resilience to domain-specific adversarial…
Jiale Lao, Immanuel Trummer · Mar 2, 2026 · Citations: 0
Automatic MetricsMathCoding
As a proof of concept, we present GenDB, an LLM-powered agentic system that generates instance-optimized and customized query execution code tailored to specific data, workloads, and hardware resources.
We implemented an early prototype of GenDB that uses Claude Code Agent as the underlying component in the multi-agent system, and we evaluate it on OLAP workloads.
Aleksei Dorkin, Taido Purason, Emil Kalbaliyev, Hele-Andra Kuulmets, Marii Ojastu, Mark Fišel · Mar 2, 2026 · Citations: 0
Pairwise PreferenceMathCoding
We subsequently apply supervised fine-tuning, preference optimization, and chat vector merging to introduce robust instruction-following behavior.
Evaluation on a comprehensive suite of Estonian benchmarks shows consistent gains in linguistic competence, knowledge, reasoning, translation quality, and instruction-following compared to the original base model and its instruction-tuned…
Xufei Lv, Jiahui Yang, Haoyuan Sun, Xialin Su, Zhiliang Tian, Yifu Gao · Mar 2, 2026 · Citations: 0
DemonstrationsCoding
Based on this insight, we propose AT2QA, an Autonomous and Training-free Agent for TKG Question Answering.
Experiments on three challenging benchmarks -- MultiTQ, Timeline-CronQuestion, and Timeline-ICEWS-Actor -- show that AT2QA achieves new state-of-the-art performance, surpassing the strongest baselines by 10.7, 4.9, and 11.2 absolute points,…
Harry Stuart, Masahiro Kaneko, Timothy Baldwin · Mar 2, 2026 · Citations: 0
Rubric RatingAutomatic MetricsCoding
Effective hiring is integral to the success of an organisation, but it is very challenging to find the most suitable candidates because expert evaluation (e.g.\ interviews conducted by a technical manager) are expensive to deploy at scale.
While prior research emphasizes the role of on-policy data in mitigating forgetting, we uncover--and validate both theoretically and empirically--an overlooked yet critical mechanism: the implicit regularization inherent in Direct…
Niu Lian, Yuting Wang, Hanshu Yao, Jinpeng Wang, Bin Chen, Yaowei Wang · Mar 2, 2026 · Citations: 0
Automatic MetricsCoding
While multimodal large language models have demonstrated impressive short-term reasoning, they struggle with long-horizon video understanding due to limited context windows and static memory mechanisms that fail to mirror human cognitive…
Extensive experiments across 4 benchmarks confirm the effectiveness of MM-Mem on both offline and streaming tasks, demonstrating robust generalization and validating the effectiveness of cognition-inspired memory organization.
Jason Lucas, Matt Murtagh-White, Adaku Uchendu, Ali Al-Lawati, Michiharu Yamashita, Dominik Macko · Feb 28, 2026 · Citations: 0
Automatic MetricsCodingMultilingual
We introduce BLUFF, a comprehensive benchmark for detecting false and synthetic content, spanning 79 languages with over 202K samples, combining human-written fact-checked content (122K+ samples across 57 languages) and LLM-generated…
We present AXL-CoI (Adversarial Cross-Lingual Agentic Chainof-Interactions), a novel multi-agentic framework for controlled fake/real news generation, paired with mPURIFY, a quality filtering pipeline ensuring dataset integrity.
Jailbreak techniques for large language models (LLMs) evolve faster than benchmarks, making robustness estimates stale and difficult to compare across papers due to drift in datasets, harnesses, and judging protocols.
We introduce JAILBREAK FOUNDRY (JBF), a system that addresses this gap via a multi-agent workflow to translate jailbreak papers into executable modules for immediate evaluation within a unified harness.
We present IDP (Intelligent Document Processing) Accelerator, a framework enabling agentic AI for end-to-end document intelligence with four key components: (1) DocSplit, a novel benchmark dataset and multimodal classifier using BIO tagging…
