首页 > 专栏 > cs.CL updates on arXiv.org cs.CL updates on arXiv.org 共 5916 条资讯 Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents 2026-06-28 03:07:22 Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL 2026-06-28 03:07:22 S3AC: Stabilized, Selective, and Scalable Actor-Critic for LLM Reasoning 2026-06-28 03:07:22 ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction 2026-06-28 03:07:22 The Butterfly Defects: Tracing Cooperation in LLM Agent Networks 2026-06-28 03:07:22 Decoupling Patient Personas and Clinical Workflows: A Dual-Agent Approach to Realistic Medical Dialogue Generation 2026-06-28 03:07:22 Accordion: Elastic-Depth Inference via Fixed-Prefix Layer Looping 2026-06-28 03:07:22 SCI-AGENT-EXAM: Benchmarking Agents on Scientific Research Tasks 2026-06-28 03:07:22 Beyond Post-Hoc Rewards: Privileged Reasoning Exploration for Multimodal Embeddings 2026-06-28 03:07:22 Profile-Driven User Simulation via Reinforcement Learning with Hierarchical Rewards for Task-Oriented Dialogues 2026-06-28 03:07:22 4DMemory: Benchmarking Long-Horizon Spatiotemporal Memory with Harness-Augmented Agents 2026-06-28 03:07:22 Can LLM Annotators Match Human Consistency? Benchmarking Human Agreement and Optimizing Multi-Agent with Contrastive Knowledge 2026-06-28 03:07:22 Head Dimension Matters in Language Models for Long-Context Retrieval 2026-06-28 03:07:22 A Broader Look into MLLM's Retrieval Heads 2026-06-28 03:07:22 Depth-Dependent Safety Geometry in Vision-Language Models: Layer-Wise Localization and Bidirectional Refusal Control 2026-06-28 03:07:22 Acoustic and Lexical Signals for Native Language Identification of Language Learners 2026-06-28 03:07:22 SyncPro: Synchronous Reasoning and Responding for Proactive Streaming Video Understanding 2026-06-28 03:07:22 Why Full-Duplex Speech Models Collapse in Long Conversations 2026-06-28 03:07:22 REACT: Representational Early Analysis and Control of Chain-of-Thought Trajectories 2026-06-28 03:07:22 Beyond Final Outcomes: Quantifying Claim-Level Information Dynamics in Multi-Agent LLM Interaction 2026-06-28 03:07:22 « 上一页1…89101112…296下一页 » 相关分类 #!/slash/note #UNTAG (B)(F)uzzing on my world (Hi)story (IN)SECURE Magazine Notification (gdb) break *0x972 - 带鱼博客 BeltfishBlog - ./kwaa.dev .NET Blog .Trash /home/rook1e 00's Adventure 0kami's Blog 0x41414141 in ?? () 0x7f Blog 0xRick Owned Root ! 0xd00's blog 1 Byte 1A23 Blog 1A23 Studio 1Link.Fun 1stwebdesigner 251 2BAB 的工程博客 2ch中文网 360 CERT 360 Netlab Blog - Network Securi 38号车评中心 3o米的微博 404 Media