Papers
R3: End-to-End Reasoning-based Planning for Multi-step Retrosynthesis via Reinforcement Learning
YiFei Wang, Qizhi Pei, Jiangtao Feng et al.
Efficient Process Reward Modeling via Contrastive Mutual Information
Nakyung Lee, Sangwoo Hong, Jungwoo Lee
Impatient Users Confuse AI Agents: High-fidelity Simulations of Human Traits for Testing Agents
Muyu He, Anand Kumar, Soumyadeep Bakshi et al.
DiVE: Decoupling Intra-layer Visual Evidence for Mitigating Hallucinations in Large Vision-Language Models
Xinwei Li, Li Lin, Hui Jiao et al.
Beyond Static Benchmarks: Synthesizing Harmful Content via Persona-based Simulation for Robust Evaluation
Huije Lee, Jisu Shin, Hoyun Song et al.
TH-RAG : Topic-Based Hierarchical Knowledge Graphs for Robust Multi-hop Reasoning in Graph-based RAG Systems
JungHyoun Kim, Soohyeong Kim, Seok Jun Hwang et al.
Characterizing the Expressivity of Local Attention in Transformers
Jiaoda Li, Ryan Cotterell
LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning
Zerui Chen, Qinggang Zhang, Zhishang Xiang et al.
From TDMA to CDMA: A Multi-bit Watermark for Diffusion Language Models
Baizhou Huang, Xiaojun Wan
ToolOmni: Enabling Open-World Tool Use via Agentic learning with Proactive Retrieval and Grounded Execution
Shouzheng Huang, Meishan Zhang, Baotian Hu et al.
On Emergent Social World Models — Evidence for Functional Integration of Theory of Mind and Pragmatic Reasoning in Language Models
Polina Tsvilodub, Jan-Felix Klumpp, Amir Pour et al.
Adaptive Retrieval for Reasoning
Jongho Kim, Jaeyoung Kim, Jihyuk Kim et al.
CSRP: Chain-of-Thought Reasoning for Chinese Text Correction via Reinforcement Learning with Efficiency-Aware Rewards
Wei Tian, Yuhao Zhou, Man Lan
Resonating with RoPE: Spectral Quantization for High-Fidelity Key Cache Compression
Xuefei Wang, Haoyu Tang, Tianyuan Liang et al.
Example Quality Matters: Multi-Aspects Example Augmentation for Private Library Programming
Yuhao Li, Haifeng Sun, Xuesong Zhang et al.
Evolutionary Negative Module Pruning for Better LoRA Merging
Anda Cao, Zhuo Gou, Yi Wang et al.
DUAL RM: Beyond Rule-based Preference Reward Modeling via Meta-Reward
Xiaobo Liang, Wanfu Wang, Qipeng Huang et al.
Beyond Markovian Forgetfulness: Episodic Memory for Reasoning-Intensive Retrieval
Dohyeon Lee, Yeonseok Jeong, Seung-won Hwang
Beyond Majority Voting: Towards Fine-grained and More Reliable Reward Signal for Test-Time Reinforcement Learning
Weiqin Wang, Yile Wang, Kehao Chen et al.
MTR-Suite: A Framework for Evaluating and Synthesizing Conversational Retrieval Benchmarks
Junhao Ruan, Abudukeyumu Abudula, Bei Li et al.
AG-GRPO: Answer-Guided GRPO for Masked Diffusion Language Models
Juhyeong Kim, Gyunyeop Kim, Sangwoo Kang
TA-GRPO-d: Trajectory-Aware GRPO for Optimizing Denoising Trajectories in Diffusion LLMs
Gyunyeop Kim, Sangwoo Kang
Glyph: Scaling Context Windows via Visual-Text Compression
Jiale Cheng, Yusen Liu, Xinyu Zhang et al.
MiniRAG: A Lightweight RAG system with Small Language Models
Tianyu Fan, Jingyuan Wang, Xubin Ren et al.