With the rapid advancement of agent-based methods in recent years, Agentic RAG has undoubtedly become an important research direction.
To address these challenges, we introduce AgenticRAGTracer, the first Agentic RAG benchmark that is primarily constructed automatically by large language models and designed to support step-by-step validation.
Yue Liu, Yingwei Ma, Yibo Miao, Yanhao Li, Yuchong Xie, Xinlong Yang · Feb 19, 2026 · Citations: 0
Rubric RatingCoding
Then, we introduce Research-Factory, an automated pipeline that generates high-quality training data by collecting research papers and constructing evaluation rubrics.
Notably, our proposed KLong (106B) surpasses Kimi K2 Thinking (1T) by 11.28% on PaperBench, and the performance improvement generalizes to other coding benchmarks like SWE-bench Verified and MLE-bench.
Generative AI is reshaping knowledge work, yet existing research focuses predominantly on software engineering and the natural sciences, with limited methodological exploration for the humanities and social sciences.
Positioned as a "methodological experiment," this study proposes an AI Agent-based collaborative research workflow (Agentic Workflow) for humanities and social science research.
Iman Ahmadi, Mehrshad Taji, Arad Mahdinezhad Kashani, AmirHossein Jadidi, Saina Kashani, Babak Khalaj · Feb 18, 2026 · Citations: 0
Simulation EnvCoding
MALLVI presents a Multi Agent Large Language and Vision framework that enables closed-loop feedback driven robotic manipulation.
Rather than using a single model, MALLVI coordinates specialized agents, Decomposer, Localizer, Thinker, and Reflector, to manage perception, localization, reasoning, and high level planning.
Safety alignment of large language models (LLMs) is mostly evaluated in English and contract-bound, leaving multilingual vulnerabilities understudied.
We introduce Indic Jailbreak Robustness (IJR), a judge-free benchmark for adversarial safety across 12 Indic and South Asian languages (2.1 Billion speakers), covering 45216 prompts in JSON (contract-bound) and Free (naturalistic) tracks.
Jeffrey T. H. Wong, Zixi Zhang, Junyi Liu, Yiren Zhao · Feb 18, 2026 · Citations: 0
Automatic MetricsMathCoding
Existing Multi-Agent Systems (MAS) typically rely on homogeneous model configurations, failing to exploit the diverse expertise inherent in different post-trained architectures.
Team-of-Thoughts introduces two novel components: (1) Orchestrator Calibration, which identifies models with superior coordination and synthesis capabilities, and (2) Agent Self-Assessment, a protocol where tool agents profile their own…
In practice, users iteratively refine visualizations through multi-turn interactions that require maintaining common ground, tracking prior edits, and adapting to evolving preferences.
We introduce ChartEditBench, a benchmark for incremental, visually grounded chart editing via code, comprising 5,000 difficulty-controlled modification chains and a rigorously human-verified subset.
Victor De Lima, Jiqun Liu, Grace Hui Yang · Feb 17, 2026 · Citations: 0
Human EvalSimulation EnvCoding
Within this framework, we construct framing-sensitive agent personas by fine-tuning language models with framing-conditioned loss attenuation, inducing targeted biases while preserving overall task competence.
Human evaluation further confirms that FrameRef's generated framings measurably affect human judgment.
Sara Rajaee, Sebastian Vincent, Alexandre Berard, Marzieh Fadaee, Kelly Marchisio, Tom Kocmi · Feb 16, 2026 · Citations: 0
Critique EditMathCoding
We systematically evaluate several open- and closed-weights RLMs on the WMT24++ benchmark and find that enabling explicit reasoning consistently degrades translation quality across languages and models.
Lingxiang Hu, Yiding Sun, Tianle Xia, Wenwei Li, Ming Xu, Liqun Liu · Feb 15, 2026 · Citations: 0
Expert VerificationSimulation EnvCoding
While Large Language Model (LLM) agents have achieved remarkable progress in complex reasoning tasks, evaluating their performance in real-world environments has become a critical problem.
To address this gap, we propose AD-Bench, a benchmark designed based on real-world business requirements of advertising and marketing platforms.
Zheng Chu, Xiao Wang, Jack Hong, Huiming Fan, Yuqi Huang, Yue Yang · Feb 15, 2026 · Citations: 0
Automatic MetricsCoding
To address these challenges, we propose REDSearcher, a unified framework that codesigns complex task synthesis, midtraining, and posttraining for scalable searchagent optimization.
Across both textonly and multimodal searchagent benchmarks, our approach achieves stateoftheart performance.
Jizheng Chen, Weiming Zhang, Xinyi Dai, Weiwen Liu, Kounianhua Du, Yasheng Wang · Feb 15, 2026 · Citations: 0
Pairwise PreferenceCoding
LogitsCoder iteratively generates and refines reasoning steps by first steering token selection toward statistically preferred patterns via Logits Preference Decoding, then selecting and aggregating diverse reasoning paths using Logits Rank…
Yet safety pipelines, benchmarks, and alignment still largely target English and a handful of high-resource languages, implicitly assuming safety and factuality ''transfer'' across languages.
We synthesize recent findings indicating that (i) safety guardrails weaken sharply on low-resource and code-mixed inputs, (ii) culturally harmful behavior can persist even when standard toxicity scores look acceptable, and (iii)…
Yuhan Cheng, Hancheng Ye, Hai Helen Li, Jingwei Sun, Yiran Chen · Feb 14, 2026 · Citations: 0
Pairwise PreferenceAutomatic MetricsCoding
We propose PrivAct, a contextual privacy-aware multi-agent learning framework that internalizes contextual privacy preservation directly into models' generation behavior for privacy-compliant agentic actions.
Experiments across multiple LLM backbones and benchmarks demonstrate consistent improvements in contextual privacy preservation, reducing leakage rates by up to 12.32% while maintaining comparable helpfulness, as well as zero-shot…
Qi Liu, Ruochen Hao, Can Li, Wanjing Ma · Feb 14, 2026 · Citations: 0
Simulation EnvCoding
We present OR-Agent, a configurable multi-agent research framework designed for automated exploration in rich experimental environments.
OR-Agent organizes research as a structured tree-based workflow that explicitly models branching hypothesis generation and systematic backtracking, enabling controlled management of research trajectories beyond simple mutation-crossover loo
Yanbo Wang, Minzheng Wang, Jian Liang, Lu Wang, Yongcan Yu, Ran He · Feb 14, 2026 · Citations: 0
Pairwise PreferenceCoding
To mitigate the safety-utility trade-off, we propose the Adaptive Safe Context Learning~(ASCL) framework to improve the reasoning given proper context.
Furthermore, to counteract the preference for rule consultation during RL, we introduce Inverse Frequency Policy Optimization~(IFPO) to rebalance advantage estimates.
