- AD-Bench: A Real-World, Trajectory-Aware Advertising Analytics Benchmark for LLM Agents
Lingxiang Hu, Yiding Sun, Tianle Xia, Wenwei Li, Ming Xu · Feb 15, 2026 · Citations: 0
Expert Verification Simulation Env Long Horizon
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.
- CricBench: A Multilingual Benchmark for Evaluating LLMs in Cricket Analytics
Vaibhav Devraj, Dhruv Kumar, Jagat Sesh Challa, Parth Agarwal, Navya Kommuri · Dec 26, 2025 · Citations: 0
Expert Verification Automatic Metrics
To investigate this potential capability gap, we present CricBench, a comprehensive benchmark suite for evaluating LLMs on specialized cricket data.
- Team of Thoughts: Efficient Test-time Scaling of Agentic Systems through Orchestrated Tool Calling
Jeffrey T. H. Wong, Zixi Zhang, Junyi Liu, Yiren Zhao · Feb 18, 2026 · Citations: 0
Expert Verification Multi Agent
Existing Multi-Agent Systems (MAS) typically rely on static, homogeneous model configurations, limiting their ability to exploit the distinct strengths of differently post-trained models.
- Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
Ailin Huang, Ang Li, Aobo Kong, Bin Wang, Binxing Jiao · Feb 11, 2026 · Citations: 0
Pairwise Preference Tool Use
We introduce Step 3.5 Flash, a sparse Mixture-of-Experts (MoE) model that bridges frontier-level agentic intelligence and computational efficiency.
- SparkMe: Adaptive Semi-Structured Interviewing for Qualitative Insight Discovery
David Anugraha, Vishakh Padmakumar, Diyi Yang · Feb 24, 2026 · Citations: 0
Expert Verification Automatic Metrics Multi Agent
Based on this formulation, we introduce SparkMe, a multi-agent LLM interviewer that performs deliberative planning via simulated conversation rollouts to select questions with high expected utility.
- Decoupling Strategy and Execution in Task-Focused Dialogue via Goal-Oriented Preference Optimization
Jingyi Xu, Xingyu Ren, Zhoupeng Shou, Yumeng Zhang, Zhiqiang You · Jan 24, 2026 · Citations: 0
Pairwise Preference Automatic Metrics Long Horizon
To address this, we propose Goal-Oriented Preference Optimization (GOPO), a hierarchical reinforcement learning framework that decouples strategy planning from response generation via an Expert Agent and a Customer Service Agent.
- KLong: Training LLM Agent for Extremely Long-horizon Tasks
Yue Liu, Zhiyuan Hu, Flood Sung, Jiaheng Zhang, Bryan Hooi · Feb 19, 2026 · Citations: 0
Rubric Rating Long Horizon
Then, we introduce Research-Factory, an automated pipeline that generates high-quality training data by collecting research papers and constructing evaluation rubrics.
- From Pixels to Policies: Reinforcing Spatial Reasoning in Language Models for Content-Aware Layout Design
Sha Li, Stefano Petrangeli, Yu Shen, Xiang Chen · Feb 14, 2026 · Citations: 0
Critique Edit Simulation Env
We introduce LaySPA, a reinforcement learning framework that equips large language models (LLMs) with explicit and interpretable spatial reasoning for content-aware graphic layout design.
- Can Large Language Models Replace Human Coders? Introducing ContentBench
Michael Haman · Feb 23, 2026 · Citations: 0
Critique Edit Automatic Metrics
This paper introduces ContentBench, a public benchmark suite that helps answer this replacement question by tracking how much agreement low-cost LLMs achieve and what they cost on the same interpretive coding tasks.
- Dyslexify: A Mechanistic Defense Against Typographic Attacks in CLIP
Lorenz Hufe, Constantin Venhoff, Erblina Purelku, Maximilian Dreyer, Sebastian Lapuschkin · Aug 28, 2025 · Citations: 0
Red Team Automatic Metrics
These models serve as suitable drop-in replacements for a broad range of safety-critical applications, where the risks of text-based manipulation outweigh the utility of text recognition.
- Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
Yihe Deng, I-Hung Hsu, Jun Yan, Zifeng Wang, Rujun Han · Oct 29, 2025 · Citations: 0
Demonstrations Long Horizon
Beyond reasoning benchmarks, SRL generalizes effectively to agentic software engineering tasks, establishing it as a robust and versatile training framework for reasoning-oriented LLMs.
- Incentivizing Agentic Reasoning in LLM Judges via Tool-Integrated Reinforcement Learning
Ran Xu, Jingjing Chen, Jiayu Ye, Yu Wu, Jun Yan · Oct 27, 2025 · Citations: 0
Pairwise Preference Human Eval
Motivated by the success of tool-integrated reasoning (TIR) in numerous tasks, we propose TIR-Judge, an end-to-end RL framework for training LLM judges that integrates a code executor for precise evaluation.
- On Discovering Algorithms for Adversarial Imitation Learning
Shashank Reddy Chirra, Jayden Teoh, Praveen Paruchuri, Pradeep Varakantham · Oct 1, 2025 · Citations: 0
Demonstrations Simulation Env
RA functions in AIL are typically derived from divergence minimization objectives, relying heavily on human design and ingenuity.
- LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?
Guozhao Mo, Wenliang Zhong, Jiawei Chen, Qianhao Yuan, Xuanang Chen · Aug 3, 2025 · Citations: 0
Llm As Judge Tool Use
Unfortunately, there is still a large gap between real-world MCP usage and current evaluation: they typically assume single-server settings and directly inject tools into the model's context, bypassing the challenges of large-scale…
- Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks
Shuo He, Lang Feng, Qi Wei, Xin Cheng, Lei Feng · Feb 26, 2026 · Citations: 0
Simulation Env Long Horizon
Group-based reinforcement learning (RL), such as GRPO, has advanced the capabilities of large language models on long-horizon agentic tasks.
- SurGo-R1: Benchmarking and Modeling Contextual Reasoning for Operative Zone in Surgical Video
Guanyi Qin, Xiaozhen Wang, Zhu Zhuo, Chang Han Low, Yuancan Xiao · Feb 25, 2026 · Citations: 0
Expert Verification Automatic Metrics
Existing AI systems offer binary safety verification or static detection, ignoring the phase-dependent nature of intraoperative reasoning.
- Diffusion Model in Latent Space for Medical Image Segmentation Task
Huynh Trinh Ngoc, Toan Nguyen Hai, Ba Luong Son, Long Tran Quoc · Dec 1, 2025 · Citations: 0
Expert Verification Automatic Metrics
Medical image segmentation is crucial for clinical diagnosis and treatment planning.
- Self-Correcting VLA: Online Action Refinement via Sparse World Imagination
Chenyv Liu, Wentao Tan, Lei Zhu, Fengling Li, Jingjing Li · Feb 25, 2026 · Citations: 0
Simulation Env Long Horizon
Reinforcement learning enhances physical grounding through exploration yet typically relies on external reward signals that remain isolated from the agent's internal states.
- CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressures
Punya Syon Pandey, Yongjin Yang, Jiarui Liu, Zhijing Jin · Aug 16, 2025 · Citations: 0
Pairwise Preference Multi Agent
Game-theoretic interactions between agents with Large Language Models (LLMs) have revealed many emergent capabilities, yet the linguistic diversity of these interactions has not been sufficiently quantified.
- Oracular Programming: A Modular Foundation for Building LLM-Enabled Software
Jonathan Laurent, André Platzer · Feb 7, 2025 · Citations: 0
Demonstrations Web Browsing
We propose oracular programming: a foundational paradigm for integrating traditional, explicit computations with inductive oracles such as LLMs.
- SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents
Patrick Tser Jern Kon, Archana Pradeep, Ang Chen, Alexander P. Ellis, Warren Hunt · Feb 25, 2026 · Citations: 0
Automatic Metrics Long Horizon
Our approach combines supervised fine-tuning on expert-augmented trajectories with agentic reinforcement learning that explicitly discourages degenerative looping and unproductive expert collaboration.
- Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language Models
Yubo Li, Xiaobin Shen, Xinyu Yao, Xueying Ding, Yidi Miao · Apr 7, 2025 · Citations: 0
Red Team Automatic Metrics
We organize existing benchmarks and datasets into coherent categories reflecting the evolving landscape of multi-turn dialogue evaluation, and review a broad spectrum of enhancement methodologies, including model-centric strategies…
- Structurally Aligned Subtask-Level Memory for Software Engineering Agents
Kangning Shen, Jingyuan Zhang, Chenxi Sun, Wencong Zeng, Yang Yue · Feb 25, 2026 · Citations: 0
Automatic Metrics Long Horizon
Large Language Models (LLMs) have demonstrated significant potential as autonomous software engineering (SWE) agents.
- ChartEditBench: Evaluating Grounded Multi-Turn Chart Editing in Multimodal Language Models
Manav Nitin Kapadnis, Lawanya Baghel, Atharva Naik, Carolyn Rosé · Feb 17, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
In practice, users iteratively refine visualizations through multi-turn interactions that require maintaining common ground, tracking prior edits, and adapting to evolving preferences.
- Precise Attribute Intensity Control in Large Language Models via Targeted Representation Editing
Rongzhi Zhang, Liqin Ye, Yuzhao Heng, Xiang Chen, Tong Yu · Oct 14, 2025 · Citations: 0
Pairwise Preference Automatic Metrics
Finally, we demonstrate efficiency enhancements across three downstream tasks: preference data synthesis, Pareto frontier approximation and optimization, and distillation of aligned behaviors for intervention-free inference.
- "Don't Do That!": Guiding Embodied Systems through Large Language Model-based Constraint Generation
Amin Seffo, Aladin Djuhera, Masataro Asai, Holger Boche · Jun 4, 2025 · Citations: 0
Simulation Env Web Browsing
Recent advancements in large language models (LLMs) have spurred interest in robotic navigation that incorporates complex spatial, mathematical, and conditional constraints from natural language into the planning problem.
- Unlocking Reasoning Capability on Machine Translation in Large Language Models
Sara Rajaee, Sebastian Vincent, Alexandre Berard, Marzieh Fadaee, Kelly Marchisio · Feb 16, 2026 · Citations: 0
Critique Edit Long Horizon
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.
- Zooming without Zooming: Region-to-Image Distillation for Fine-Grained Multimodal Perception
Lai Wei, Liangbo He, Jun Lan, Lingzhong Dong, Yutong Cai · Feb 12, 2026 · Citations: 0
Automatic Metrics Tool Use
To address this, we propose Region-to-Image Distillation, which transforms zooming from an inference-time tool into a training-time primitive, thereby internalizing the benefits of agentic zooming into a single forward pass of an MLLM.
- AceGRPO: Adaptive Curriculum Enhanced Group Relative Policy Optimization for Autonomous Machine Learning Engineering
Yuzhu Cai, Zexi Liu, Xinyu Zhu, Cheng Wang, Siheng Chen · Feb 8, 2026 · Citations: 0
Automatic Metrics Long Horizon
Autonomous Machine Learning Engineering (MLE) requires agents to perform sustained, iterative optimization over long horizons.
- KBVQ-MoE: KLT-guided SVD with Bias-Corrected Vector Quantization for MoE Large Language Models
Zukang Xu, Zhixiong Zhao, Xing Hu, Zhixuan Chen, Dawei Yang · Jan 30, 2026 · Citations: 0
Automatic MetricsSimulation Env
Mixture of Experts (MoE) models have achieved great success by significantly improving performance while maintaining computational efficiency through sparse expert activation.
- Diffusion Generative Recommendation with Continuous Tokens
Haohao Qu, Shanru Lin, Yujuan Ding, Yiqi Wang, Wenqi Fan · Apr 16, 2025 · Citations: 0
Pairwise Preference Automatic Metrics
Specifically, ContRec consists of two key modules: a sigma-VAE Tokenizer, which encodes users/items with continuous tokens; and a Dispersive Diffusion module, which captures implicit user preference.
- Test-Time Scaling with Diffusion Language Models via Reward-Guided Stitching
Roy Miles, Aysim Toker, Andreea-Maria Oncescu, Songcen Xu, Jiankang Deng · Feb 26, 2026 · Citations: 0
Automatic Metrics Long Horizon
This modular pipeline separates exploration (diffusion) from evaluation and solution synthesis, avoiding monolithic unified hybrids while preserving broad search.
- Continuous Telemonitoring of Heart Failure using Personalised Speech Dynamics
Yue Pan, Xingyao Wang, Hanyue Zhang, Liwei Liu, Changxin Li · Feb 23, 2026 · Citations: 0
Automatic Metrics Long Horizon
The model's high sensitivity was further corroborated by additional follow-up data, confirming its efficacy in predicting HF deterioration and its potential to secure patient safety in remote, home-based settings.
- REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents
Zheng Chu, Xiao Wang, Jack Hong, Huiming Fan, Yuqi Huang · Feb 15, 2026 · Citations: 0
Automatic Metrics Tool Use
To address these challenges, we propose REDSearcher, a unified framework that codesigns complex task synthesis, midtraining, and posttraining for scalable searchagent optimization.
- RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility
Haoyu He, Haozheng Luo, Yan Chen, Qi R. Wang · Sep 27, 2025 · Citations: 0
Automatic Metrics Long Horizon
Predicting human mobility is inherently challenging due to complex long-range dependencies and multi-scale periodic behaviors.
- Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation
Wenkai Yang, Weijie Liu, Ruobing Xie, Kai Yang, Saiyong Yang · Feb 12, 2026 · Citations: 0
Expert Verification
Then, we propose the Generalized On-Policy Distillation (G-OPD) framework, which extends the standard OPD objective by introducing a flexible reference model and a reward scaling factor that controls the relative weight of the reward term…
- MALLVI: A Multi-Agent Framework for Integrated Generalized Robotics Manipulation
Iman Ahmadi, Mehrshad Taji, Arad Mahdinezhad Kashani, AmirHossein Jadidi, Saina Kashani · Feb 18, 2026 · Citations: 0
Simulation Env Multi Agent
MALLVI presents a Multi Agent Large Language and Vision framework that enables closed-loop feedback driven robotic manipulation.
- OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Algorithm Discovery
Qi Liu, Ruochen Hao, Can Li, Wanjing Ma · Feb 14, 2026 · Citations: 0
Simulation Env Multi Agent
We present OR-Agent, a configurable multi-agent research framework designed for automated exploration in rich experimental environments.
- World Simulation with Video Foundation Models for Physical AI
NVIDIA, :, Arslan Ali, Junjie Bai, Maciej Bala · Oct 28, 2025 · Citations: 0
Simulation Env Long Horizon
These capabilities enable more reliable synthetic data generation, policy evaluation, and closed-loop simulation for robotics and autonomous systems.
- AgentDropoutV2: Optimizing Information Flow in Multi-Agent Systems via Test-Time Rectify-or-Reject Pruning
Yutong Wang, Siyuan Xiong, Xuebo Liu, Wenkang Zhou, Liang Ding · Feb 26, 2026 · Citations: 0
Automatic Metrics Multi Agent
We propose AgentDropoutV2, a test-time rectify-or-reject pruning framework designed to dynamically optimize MAS information flow without retraining.
- A Benchmark for Deep Information Synthesis
Debjit Paul, Daniel Murphy, Milan Gritta, Ronald Cardenas, Victor Prokhorov · Feb 24, 2026 · Citations: 0
Automatic Metrics Tool Use
To address this, we introduce DEEPSYNTH, a novel benchmark designed to evaluate agents on realistic, time-consuming problems that combine information gathering, synthesis, and structured reasoning to produce insights.
- Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces
Shreyas Rajesh, Pavan Holur, Chenda Duan, David Chong, Vwani Roychowdhury · Nov 10, 2025 · Citations: 0
Automatic Metrics Long Horizon
On the Episodic Memory Benchmark (EpBench) huet_episodic_2025 comprising corpora ranging from 100k to 1M tokens in length, GSW outperforms existing RAG based baselines by up to 20\%.
- Counterfactual Simulation Training for Chain-of-Thought Faithfulness
Peter Hase, Christopher Potts · Feb 24, 2026 · Citations: 0
Automatic MetricsSimulation Env
In this paper, we introduce a training method called Counterfactual Simulation Training (CST), which aims to improve CoT faithfulness by rewarding CoTs that enable a simulator to accurately predict a model's outputs over counterfactual…
- From Labor to Collaboration: A Methodological Experiment Using AI Agents to Augment Research Perspectives in Taiwan's Humanities and Social Sciences
Yi-Chih Huang · Feb 19, 2026 · Citations: 0
Demonstrations
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.
- Persona-driven Simulation of Voting Behavior in the European Parliament with Large Language Models
Maximilian Kreutner, Marlene Lutz, Markus Strohmaier · Jun 13, 2025 · Citations: 0
Automatic MetricsSimulation Env
We evaluate whether predictions are stable in response to counterfactual arguments, different persona prompts, and generation methods.
- GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL
Rui Yang, Qianhui Wu, Zhaoyang Wang, Hanyang Chen, Ke Yang · Feb 25, 2026 · Citations: 0
Automatic Metrics Long Horizon
Open-source native GUI agents still lag behind closed-source systems on long-horizon navigation tasks.
- Classroom Final Exam: An Instructor-Tested Reasoning Benchmark
Chongyang Gao, Diji Yang, Shuyan Zhou, Xichen Yan, Luchuan Song · Feb 23, 2026 · Citations: 0
Automatic Metrics Long Horizon
We introduce (Classroom Final Exam), a multimodal benchmark for evaluating the reasoning capabilities of large language models across more than 20 STEM domains.
- Natural Language Declarative Prompting (NLD-P): A Modular Governance Method for Prompt Design Under Model Drift
Hyunwoo Kim, Hanau Yi, Jaehee Bae, Yumin Kim · Feb 26, 2026 · Citations: 0
Critique Edit
NLD-P is formalized as a modular control abstraction that separates provenance, constraint logic, task content, and post-generation evaluation, encoded directly in natural language without reliance on external orchestration code.
- Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination
Rakshit Trivedi, Kartik Sharma, David C Parkes · Feb 24, 2026 · Citations: 0
Demonstrations
Effective human-AI coordination requires artificial agents capable of exhibiting and responding to human-like behaviors while adapting to changing contexts.
- IndicJR: A Judge-Free Benchmark of Jailbreak Robustness in South Asian Languages
Priyaranjan Pattnayak, Sanchari Chowdhuri · Feb 18, 2026 · Citations: 0
Red Team
Safety alignment of large language models (LLMs) is mostly evaluated in English and contract-bound, leaving multilingual vulnerabilities understudied.
- Programming by Backprop: An Instruction is Worth 100 Examples When Finetuning LLMs
Jonathan Cook, Silvia Sapora, Arash Ahmadian, Akbir Khan, Tim Rocktaschel · Jun 23, 2025 · Citations: 0
Demonstrations
Though execution of instructions in training data remains less reliable than when instructions are given in-context, our results demonstrate that procedural knowledge can be noisily `programmed' into LLMs through PBB, with important…
- A Hierarchical Multi-Agent System for Autonomous Discovery in Geoscientific Data Archives
Dmitrii Pantiukhin, Ivan Kuznetsov, Boris Shapkin, Antonia Anna Jost, Thomas Jung · Feb 24, 2026 · Citations: 0
Automatic Metrics Long Horizon
Here we present PANGAEA-GPT, a hierarchical multi-agent framework designed for autonomous data discovery and analysis.
