- Towards Better RL Training Data Utilization via Second-Order Rollout
Zhe Yang, Yudong Wang, Rang Li, Zhifang Sui · Feb 26, 2026 · Citations: 0
Critique Edit Automatic Metrics
Reinforcement Learning (RL) has empowered Large Language Models (LLMs) with strong reasoning capabilities, but vanilla RL mainly focuses on generation capability improvement by training with only first-order rollout (generating multiple res
- Beyond Refusal: Probing the Limits of Agentic Self-Correction for Semantic Sensitive Information
Umid Suleymanov, Zaur Rajabov, Emil Mirzazada, Murat Kantarcioglu · Feb 25, 2026 · Citations: 0
Critique Edit Automatic Metrics
To address this, we introduce SemSIEdit, an inference-time framework where an agentic "Editor" iteratively critiques and rewrites sensitive spans to preserve narrative flow rather than simply refusing to answer.
- CAMEL: Confidence-Gated Reflection for Reward Modeling
Zirui Zhu, Hailun Xu, Yang Luo, Yong Liu, Kanchan Sarkar · Feb 24, 2026 · Citations: 0
Pairwise PreferenceCritique Edit Automatic Metrics
Reward models play a fundamental role in aligning large language models with human preferences.
- Tool-Aware Planning in Contact Center AI: Evaluating LLMs through Lineage-Guided Query Decomposition
Varun Nathan, Shreyas Guha, Ayush Kumar · Feb 16, 2026 · Citations: 0
Critique Edit Automatic Metrics
We present a domain-grounded framework and benchmark for tool-aware plan generation in contact centers, where answering a query for business insights, our target use case, requires decomposing it into executable steps over structured tools
- Large Language Models and Impossible Language Acquisition: "False Promise" or an Overturn of our Current Perspective towards AI
Ziyan Wang, Longlong Ma · Feb 9, 2026 · Citations: 0
Critique Edit Automatic Metrics
In Chomsky's provocative critique "The False Promise of CHATGPT," Large Language Models (LLMs) are characterized as mere pattern predictors that do not acquire languages via intrinsic causal and self-correction structures like humans, there
- RebuttalAgent: Strategic Persuasion in Academic Rebuttal via Theory of Mind
Zhitao He, Zongwei Lyu, Yi R Fung · Jan 22, 2026 · Citations: 0
Pairwise PreferenceCritique Edit Human Eval
In this paper, we introduce RebuttalAgent, the first framework to ground academic rebuttal in Theory of Mind (ToM), operationalized through a ToM-Strategy-Response (TSR) framework that models reviewer mental state, formulates persuasion str
- VULCA-Bench: A Multicultural Vision-Language Benchmark for Evaluating Cultural Understanding
Haorui Yu, Diji Yang, Hang He, Fengrui Zhang, Qiufeng Yi · Jan 12, 2026 · Citations: 0
Critique Edit Automatic Metrics
We introduce VULCA-Bench, a multicultural art-critique benchmark for evaluating Vision-Language Models' (VLMs) cultural understanding beyond surface-level visual perception.
- Reward Modeling from Natural Language Human Feedback
Zongqi Wang, Rui Wang, Yuchuan Wu, Yiyao Yu, Pinyi Zhang · Jan 12, 2026 · Citations: 0
Pairwise PreferenceCritique Edit Automatic Metrics
Reinforcement Learning with Verifiable reward (RLVR) on preference data has become the mainstream approach for training Generative Reward Models (GRMs).
- Multimodal Peer Review Simulation with Actionable To-Do Recommendations for Community-Aware Manuscript Revisions
Mengze Hong, Di Jiang, Weiwei Zhao, Yawen Li, Yihang Wang · Nov 14, 2025 · Citations: 0
Critique Edit Simulation Env
Experimental results highlight the effectiveness of the proposed system in generating more comprehensive and useful reviews aligned with expert standards, surpassing ablated baselines and advancing transparent, human-centered scholarly assi
- Error-Aware Knowledge Distillation via Targeted Revision for Customer-Service Summarization
Hee-Jin Lee, Zhen Guo, Luchao Jin, Morteza Moazami Goudarzi · Nov 4, 2025 · Citations: 0
Critique Edit Automatic Metrics
We introduce an Analyze-Revise-Finetune (ARF) pipeline that enables smaller open-source language models (LLMs) to surpass substantially larger proprietary models in customer service summarization tasks.
- SocialHarmBench: Revealing LLM Vulnerabilities to Socially Harmful Requests
Punya Syon Pandey, Hai Son Le, Devansh Bhardwaj, Rada Mihalcea, Zhijing Jin · Oct 6, 2025 · Citations: 0
Critique Edit Automatic Metrics
Yet, existing safety benchmarks rarely test vulnerabilities in domains such as political manipulation, propaganda and disinformation generation, or surveillance and information control.
- ClearFairy: Capturing Creative Workflows through Decision Structuring, In-Situ Questioning, and Rationale Inference
Kihoon Son, DaEun Choi, Tae Soo Kim, Young-Ho Kim, Sangdoo Yun · Sep 18, 2025 · Citations: 0
Critique Edit Automatic Metrics
Furthermore, exploratory applications demonstrate that captured steps can enhance generative AI agents in Figma, yielding predictions better aligned with professionals and producing coherent outcomes.
- TASER: Table Agents for Schema-guided Extraction and Recommendation
Nicole Cho, Kirsty Fielding, William Watson, Sumitra Ganesh, Manuela Veloso · Aug 18, 2025 · Citations: 0
Critique Edit Automatic Metrics
To address this, we present TASER (Table Agents for Schema-guided Extraction and Recommendation), a continuously learning, agentic table extraction system that converts highly unstructured, multi-page, heterogeneous tables into normalized,
- Critique-GRPO: Advancing LLM Reasoning with Natural Language and Numerical Feedback
Xiaoying Zhang, Yipeng Zhang, Hao Sun, Kaituo Feng, Chaochao Lu · Jun 3, 2025 · Citations: 0
Critique Edit Automatic Metrics
Recent advances in reinforcement learning (RL) using numerical rewards have significantly enhanced the complex reasoning capabilities of large language models (LLMs).
- SEFL: A Framework for Generating Synthetic Educational Assignment Feedback with LLM Agents
Mike Zhang, Amalie Pernille Dilling, Léon Gondelman, Niels Erik Ruan Lyngdorf, Euan D. Lindsay · Feb 18, 2025 · Citations: 0
Critique Edit Automatic Metrics
Through comprehensive evaluations with three LLM judges and three human experts, across a subset of 900 outputs, we demonstrate that SEFL-tuned models outperform both their untuned counterparts and an existing baseline in terms of feedback
