Tracked topic
Large language models are machine learning models trained to predict and generate text and other language-based outputs.
…Training LLM Agents via Agent-Data Mutual Evolution (2026) DPEPO: Diverse Parallel Exploration Policy Optimization for LLM-based Agents (2026) COMAP: Co-Evolving World Models and Agent Policies for LLM Agents (2026…
Papers arxiv:2608.06485 Do AI Personas Grow? Analyzing and Benchmarking Personality Evolution in LLM Agents After Life Events Published on Aug 6 Submitted by Ming Wang on Aug 10 KinaMind Authors…
…A Data-Centric Survey of Privacy in LLM Agents (2026) PrivacyAlign: Contextual Privacy Alignment for LLM Agents (2026) MuPPET: A Benchmark for Contextual Privacy of LLM Assistants in Multi-Party Conversations (2026…
Papers arxiv:2606.04703 Rethinking Continual Experience Internalization for Self-Evolving LLM Agents Published on Jun 3 Submitted by Wenkai Yang on Jun 5 Authors: Jingwen Chen , Wenkai Yang , , , , , , , , Abstract Experience internalization…
…View arXiv page View PDF Add to collection Community Autonomous training for large language models (LLMs) is entering a new era. Rather than relying on a static recipe, EvoTrainer enables LLM policies…
…The following papers were recommended by the Semantic Scholar API Diagnosing Training Inference Mismatch in LLM Reinforcement Learning (2026) AIS: Adaptive Importance Sampling for Quantized RL (2026) Reformulate LLM Reinforcement Learning for…
…This has driven widespread reliance on automated approaches such as LLM-as-a-judge (LLMJ) to critique agents at the process and outcome-levels at scale, however, the soundness of LLMJ critiques…
…Towards Zero-Shot Generalization on Text-Attributed Graphs with LLMs (2026) PromptGNN-sim: Deep Fusion and Alignment of GNN and LLMs for Text-Attributed Graph Learning (2026) Enhancing LLMs for Graph Tasks…
…Text-Guided Flow Matching in Activation Space for Versatile LLM Steering Published on May 28 Submitted by yingdong shi on May 29 ShanghaiTech University Authors: , , , , , , Abstract UniSteer uses text-guided activation flow…
Papers arxiv:2606.09821 Rethinking the Divergence Regularization in LLM RL Published on Jun 8 Submitted by Xiangxin Zhou on Jun 10 Tencent-Hunyuan-Multimodal-RL Authors: , Xiangxin Zhou , Penghui Qi , , , Tianyu…