Tracked topic
Large language models are machine learning models trained to predict and generate text and other language-based outputs.
…A Benchmark for Evaluating Multilingual LLM Safety in South Asia (2026) ML-Bench&Guard: Policy-Grounded Multilingual Safety Benchmark and Guardrail for Large Language Models (2026) HarmChip: Evaluating Hardware Security Centric LLM…
Papers arxiv:2606.07867 The Cold-Start Safety Gap in LLM Agents Published on Jun 5 Submitted by Chung-En, Sun on Jun 12 Authors: Chung-En Sun , , Abstract Tool-calling language…
Papers arxiv:2606.28186 Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction Published on Jun 26 Submitted by Ming Li on Jun 30 Authors: , , , , , , Abstract Epi2Diff framework transforms…
…A key idea is LLM-as-Observer: instead of asking an LLM to directly predict the next action, we let a small frozen LLM read the interaction and use its hidden states…
…Iterative Co-Training of LLM Rewriter & Dense Encoder for Tool Retrieval Published on May 28 Submitted by Ashutosh Hathidara on May 29 SAP Authors: , Ashutosh Hathidara , Abstract CoHyDE is an iterative method…
…Exploratory RL for LLM Mid-Training Published on Jun 15 Submitted by Violet Xiang on Jun 16 Stanford University Authors: Violet Xiang , , , , Abstract ExpRL uses human-written question-answer data as reward…
…Disentangling Evolution Capabilities in Self-Evolving LLM Agents (2026) Bayesian-Agent: Posterior-Guided Skill Evolution for LLM Agent Harnesses (2026) SkillAdaptor: Self-Adapting Skills for LLM Agents from Trajectories (2026) Please give…
…Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents Published on Jun 30 Submitted by Matteo Merler on Jul 1 Bethgelab Authors: Sergio Hernández-Gutiérrez , Matteo Merler , , , , Abstract A testbed called…
Papers arxiv:2606.14061 LLM Agents Can See Code Repositories Published on Jun 12 Submitted by Silin Chen on Jun 15 Shanghai Jiao Tong University Authors: , Silin Chen , , , , Abstract Visual repository representations…
Papers arxiv:2605.30159 Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM Agents Published on May 28 Submitted by liu on Jun 5 university of science and technology of china Authors…