- PRBench: End-to-end Paper Reproduction in Physics Research
Shi Qiu, Junyi Deng, Yiwei Deng, Haoran Dong, Jieyu Fu · Mar 29, 2026 · Citations: 0
Rubric RatingExpert Verification Automatic MetricsSimulation Env
We introduce PRBench, a benchmark of 30 expert-curated tasks spanning 11 subfields of physics.
- Paper Reconstruction Evaluation: Evaluating Presentation and Hallucination in AI-written Papers
Atsuyuki Miyai, Mashiro Toyooka, Zaiying Zhao, Kenta Watanabe, Toshihiko Yamasaki · Apr 1, 2026 · Citations: 0
Rubric Rating Automatic Metrics
We introduce Paper Reconstruction Evaluation (PaperRecon), an evaluation framework in which an overview (overview.md) is created from an existing paper, after which an agent generates a full paper based on the overview and minimal…
- Modeling and Benchmarking Spoken Dialogue Rewards with Modality and Colloquialness
Jingyu Lu, Yuhan Wang, Fan Zhuo, Xize Cheng, Changhao Pan · Mar 16, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
To address these challenges, we introduce SDiaReward, an end-to-end multi-turn reward model trained on SDiaReward-Dataset, a novel collection of episode-level preference pairs explicitly targeting these gaps.
- Do Phone-Use Agents Respect Your Privacy?
Zhengyang Tang, Ke Ji, Xidong Wang, Zihan Ye, Xinyuan Wang · Apr 1, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
We study whether phone-use agents respect privacy while completing benign mobile tasks.
- CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbacks
Hao Wang, Licheng Pan, Zhichao Chen, Chunyuan Zheng, Zhixuan Chu · Mar 19, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
Despite the success of reinforcement learning from human feedback (RLHF) in aligning language models, current reward modeling heavily relies on experimental feedback data collected from human annotators under controlled and costly…
- Sabiá-4 Technical Report
Thiago Laitz, Thales Sales Almeida, Hugo Abonizio, Roseval Malaquias Junior, Giovana Kerche Bonás · Mar 10, 2026 · Citations: 0
Pairwise Preference Automatic Metrics Tool Use
The models were developed through a four-stage training pipeline: continued pre-training on Portuguese and Brazilian legal corpora, long-context extension to 128K tokens, supervised fine-tuning on instruction data spanning chat, code, legal…
- QED-Nano: Teaching a Tiny Model to Prove Hard Theorems
LM-Provers, Yuxiao Qu, Amrith Setlur, Jasper Dekoninck, Edward Beeching · Apr 6, 2026 · Citations: 0
Rubric Rating Automatic Metrics
To support further research on open mathematical reasoning, we release the full QED-Nano pipeline, including the QED-Nano and QED-Nano-SFT models, the FineProofs-SFT and FineProofs-RL datasets, and the training and evaluation code.
- LLM-Powered Workflow Optimization for Multidisciplinary Software Development: An Automotive Industry Case Study
Shuai Wang, Yinan Yu, Earl Barr, Dhasarathy Parthasarathy · Mar 22, 2026 · Citations: 0
Expert Verification Automatic Metrics
We evaluate our approach on spapi, a production in-vehicle API system at Volvo Group involving 192 endpoints, 420 properties, and 776 CAN signals across six functional domains.
- S0 Tuning: Zero-Overhead Adaptation of Hybrid Recurrent-Attention Models
Jack Young · Apr 1, 2026 · Citations: 0
Automatic Metrics Long Horizon
Using roughly 48 execution-verified HumanEval training solutions, tuning a single initial state matrix per recurrent layer, with zero inference overhead, outperforms LoRA by +10.8 pp (p < 0.001) on HumanEval.
- Grounding Arabic LLMs in the Doha Historical Dictionary: Retrieval-Augmented Understanding of Quran and Hadith
Somaya Eltanbouly, Samer Rashwani · Mar 25, 2026 · Citations: 0
Human EvalLlm As Judge
Gemini also serves as an LLM-as-a-judge system for automatic evaluation in our experiments.
- Criterion-referenceability determines LLM-as-a-judge validity across physics assessment formats
Will Yeadon, Tom Hardy, Paul Mackay, Elise Agra · Mar 16, 2026 · Citations: 0
Llm As JudgeAutomatic Metrics
We evaluate LLM-as-a-judge marking across three physics assessment formats - structured questions, written essays, and scientific plots - comparing GPT-5.2, Grok 4.1, Claude Opus 4.5, DeepSeek-V3.2, Gemini Pro 3, and committee aggregations…
- IslamicMMLU: A Benchmark for Evaluating LLMs on Islamic Knowledge
Ali Abdelaal, Mohammed Nader Al Haffar, Mahmoud Fawzi, Walid Magdy · Mar 24, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
We introduce IslamicMMLU, a benchmark of 10,013 multiple-choice questions spanning three tracks: Quran (2,013 questions), Hadith (4,000 questions), and Fiqh (jurisprudence, 4,000 questions).
- Truth as a Compression Artifact in Language Model Training
Konstantin Krestnikov · Mar 12, 2026 · Citations: 0
Pairwise Preference Automatic Metrics
In the random-error setting, models strongly prefer correct completions in paired evaluation: 83.1% accuracy at balanced data and 67.0% even when correct rules appear in only 10% of the corpus.
- Courtroom-Style Multi-Agent Debate with Progressive RAG and Role-Switching for Controversial Claim Verification
Masnun Nuha Chowdhury, Nusrat Jahan Beg, Umme Hunny Khan, Syed Rifat Raiyan, Md Kamrul Hasan · Mar 30, 2026 · Citations: 0
Automatic Metrics Multi Agent
We propose a courtroom-style multi-agent framework, PROClaim, that reformulates verification as a structured, adversarial deliberation.
- SkillX: Automatically Constructing Skill Knowledge Bases for Agents
Chenxi Wang, Zhuoyun Yu, Xin Xie, Wuguannan Yao, Runnan Fang · Apr 6, 2026 · Citations: 0
Automatic Metrics Long Horizon
Learning from experience is critical for building capable large language model (LLM) agents, yet prevailing self-evolving paradigms remain inefficient: agents learn in isolation, repeatedly rediscover similar behaviors from limited…
- Agent Q-Mix: Selecting the Right Action for LLM Multi-Agent Systems through Reinforcement Learning
Eric Hanchen Jiang, Levina Li, Rui Sun, Xiao Liang, Yubei Li · Apr 1, 2026 · Citations: 0
Automatic Metrics Multi Agent
In this paper, we propose Agent Q-Mix, a reinforcement learning framework that reformulates topology selection as a cooperative Multi-Agent Reinforcement Learning (MARL) problem.
- LRC-WeatherNet: LiDAR, RADAR, and Camera Fusion Network for Real-time Weather-type Classification in Autonomous Driving
Nour Alhuda Albashir, Lars Pernickel, Danial Hamoud, Idriss Gouigah, Eren Erdal Aksoy · Mar 23, 2026 · Citations: 0
Automatic Metrics Web Browsing
Autonomous vehicles face major perception and navigation challenges in adverse weather such as rain, fog, and snow, which degrade the performance of LiDAR, RADAR, and RGB camera sensors.
- Effective Strategies for Asynchronous Software Engineering Agents
Jiayi Geng, Graham Neubig · Mar 23, 2026 · Citations: 0
Automatic Metrics Long Horizon
Inspired by these collaboration primitives, we introduce Centralized Asynchronous Isolated Delegation (CAID), a structured multi-agent coordination paradigm grounded in three core SWE primitives: centralized task delegation, asynchronous…
- Cross-Context Verification: Hierarchical Detection of Benchmark Contamination through Session-Isolated Analysis
Tae-Eun Song · Mar 23, 2026 · Citations: 0
Automatic Metrics Multi Agent
LLM coding benchmarks face a credibility crisis: widespread solution leakage and test quality issues undermine SWE-bench Verified, while existing detection methods--paraphrase consistency, n-gram overlap, perplexity analysis--never directly…
- ToolFlood: Beyond Selection -- Hiding Valid Tools from LLM Agents via Semantic Covering
Hussein Jawad, Nicolas J-B Brunel · Mar 14, 2026 · Citations: 0
Automatic Metrics Tool Use
Large Language Model (LLM) agents increasingly use external tools for complex tasks and rely on embedding-based retrieval to select a small top-k subset for reasoning.
- Learning to Predict Future-Aligned Research Proposals with Language Models
Heng Wang, Pengcheng Jiang, Jiashuo Sun, Zhiyi Shi, Haofei Yu · Mar 28, 2026 · Citations: 0
Human EvalAutomatic Metrics
Across Llama-3.1 and Qwen2.5 models, future-aligned tuning improves future alignment over unaligned baselines (up to +10.6% overall FAS), and domain-expert human evaluation corroborates improved proposal quality.
- Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework
Komal Kumar, Aman Chadha, Salman Khan, Fahad Shahbaz Khan, Hisham Cholakkal · Apr 7, 2026 · Citations: 0
Automatic Metrics Multi Agent
Recent advances in multi-agent large language models (LLMs) have demonstrated strong potential for understanding user intent and are being trained to utilize various tools.
- Scaling Reasoning Tokens via RL and Parallel Thinking: Evidence From Competitive Programming
Qianfan Zhang, Tianyu Guo, Xuandi Ren, Jiale Chen, Ming Ding · Apr 1, 2026 · Citations: 0
Automatic Metrics Long Horizon
During RL training, we observe an approximately log-linear relationship between validation accuracy and the average number of generated reasoning tokens over successive checkpoints, and show two ways to shift this training trajectory:…
- TRIMS: Trajectory-Ranked Instruction Masked Supervision for Diffusion Language Models
Lingjie Chen, Ruizhong Qiu, Yuyu Fan, Yanjun Zhao, Hanghang Tong · Apr 1, 2026 · Citations: 0
Automatic Metrics Long Horizon
Experiments on LLaDA and Dream across math and coding benchmarks show that TRIMS significantly improves the accuracy-parallelism trade-off over both standard MDLM training and train-free acceleration baselines, while achieving competitive…
- The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestration
Haoyuan Xu, Chang Li, Xinyan Ma, Xianhao Ou, Zihan Zhang · Mar 24, 2026 · Citations: 0
Automatic Metrics Tool Use
As agent systems evolve, however, the central problem has shifted from isolated invocation to multi-tool orchestration over long trajectories with intermediate state, execution feedback, changing environments, and practical constraints such…
- EndoCoT: Scaling Endogenous Chain-of-Thought Reasoning in Diffusion Models
Xuanlang Dai, Yujie Zhou, Long Xing, Jiazi Bu, Xilin Wei · Mar 12, 2026 · Citations: 0
Automatic Metrics Long Horizon
Extensive evaluations across diverse benchmarks (e.g., Maze, TSP, VSP, and Sudoku) achieve an average accuracy of 92.1%, outperforming the strongest baseline by 8.3 percentage points.
- The Detection--Extraction Gap: Models Know the Answer Before They Can Say It
Hanyang Wang, Mingxuan Zhu · Apr 8, 2026 · Citations: 0
Automatic Metrics Tool Use
Across five model configurations, two families, and three benchmarks, we find that 52--88\% of chain-of-thought tokens are produced after the answer is recoverable from a partial prefix.
- AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning
Yuanfu Sun, Kang Li, Dongzhe Fan, Jiajin Liu, Qiaoyu Tan · Apr 7, 2026 · Citations: 0
Automatic Metrics Tool Use
To bridge this gap, we introduce Agentic Graph Learning (AGL), a paradigm that reframes graph learning as an interleaved process of topology-aware navigation and LLM-based inference.
- From Guessing to Placeholding: A Cost-Theoretic Framework for Uncertainty-Aware Code Completion
Liang Zhu, Haolin Chen, Lidong Zhao, Xian Wu · Apr 2, 2026 · Citations: 0
Automatic Metrics Web Browsing
Extensive evaluations across 1.5B--14B parameter models demonstrate that APC reduces expected editing costs from 19% to 50% while preserving standard HC performance.
- Oblivion: Self-Adaptive Agentic Memory Control through Decay-Driven Activation
Ashish Rana, Chia-Chien Hung, Qumeng Sun, Julian Martin Kunkel, Carolin Lawrence · Mar 31, 2026 · Citations: 0
Automatic Metrics Long Horizon
Human memory adapts through selective forgetting: experiences become less accessible over time but can be reactivated by reinforcement or contextual cues.
- Hierarchical Chain-of-Thought Prompting: Enhancing LLM Reasoning Performance and Efficiency
Xingshuai Huang, Derek Li, Bahareh Nikpour, Parsa Omidi · Mar 31, 2026 · Citations: 0
Automatic Metrics Long Horizon
Extensive evaluations across diverse LLMs and mathematical reasoning benchmarks show that Hi-CoT consistently improves average accuracy by 6.2% (up to 61.4% on certain models and tasks) while reducing reasoning trace length by 13.9%…
- Mi:dm K 2.5 Pro
KT Tech innovation Group · Mar 19, 2026 · Citations: 0
Automatic Metrics Long Horizon
The evolving LLM landscape requires capabilities beyond simple text generation, prioritizing multi-step reasoning, long-context understanding, and agentic workflows.
- MedMASLab: A Unified Orchestration Framework for Benchmarking Multimodal Medical Multi-Agent Systems
Yunhang Qian, Xiaobin Hu, Jiaquan Yu, Siyang Xin, Xiaokun Chen · Mar 10, 2026 · Citations: 0
Automatic Metrics Multi Agent
While Multi-Agent Systems (MAS) show potential for complex clinical decision support, the field remains hindered by architectural fragmentation and the lack of standardized multimodal integration.