3,698 items tracked: 33 reported by two or more outlets, the rest by a single source. Most-corroborated first.
arXiv:2605.08374v4 Announce Type: replace Abstract: Episodic memory allows LLM agents to accumulate and retrieve experience, but current methods treat each memory independently, i.e., evaluating retrieval quality in isol…
arXiv:2605.08703v2 Announce Type: replace Abstract: Aligning generative models with human preferences remains a central challenge.
arXiv:2605.09129v2 Announce Type: replace Abstract: Circuit study aims to explain how language models (LMs) implement a task by localizing and interpreting a circuit: a computational subgraph responsible for a specific m…
arXiv:2605.10325v3 Announce Type: replace Abstract: Reinforcement learning from verifiable rewards (RLVR) has improved the reasoning capabilities of large language models (LLMs), yet existing approaches predominantly rel…
arXiv:2605.22883v2 Announce Type: replace Abstract: Current AI energy benchmarks measure consumption per model invocation.
arXiv:2605.26911v2 Announce Type: replace Abstract: LLM-generated peer reviews are increasingly common at major venues, yet their deficiencies are hard to detect because they are uniformly fluent and well-structured.
arXiv:2606.00756v2 Announce Type: replace Abstract: LLM-based Web agents are increasingly deployed on edge servers to carry out long-horizon tasks on behalf of users with low latency.
arXiv:2606.10044v3 Announce Type: replace Abstract: World model has emerged as a powerful paradigm in artificial intelligence, enabling agents to represent their environments, predict future states, and evaluate possible…
arXiv:2606.18060v2 Announce Type: replace Abstract: As Large Language Model based agents enter autonomous scientific research, their ability to resist pseudoscience becomes increasingly important.
arXiv:2606.18947v2 Announce Type: replace Abstract: Production LLM agents increasingly depend on real-time search, yet native search grounding bundles retrieval policy, provider choice, evidence injection, cost, latency,…
arXiv:2606.19990v3 Announce Type: replace Abstract: While RL has become a promising tool for refining world models, existing methods largely rely on conservative rollouts near the training distribution, limiting explorat…
arXiv:2606.22936v2 Announce Type: replace Abstract: Tool-using LLM agents make early choices about what to search for, which evidence to trust, and what to do next.
arXiv:2606.22953v2 Announce Type: replace Abstract: Context managers summarize or evict old messages so agents can operate beyond a finite window.
arXiv:2606.24064v2 Announce Type: replace Abstract: Distilling reasoning capabilities from strong to weak language models typically involves imitating specific solution trajectories, effectively transferring what to answ…
arXiv:2606.27780v3 Announce Type: replace Abstract: World models are increasingly used for planning by predicting future states under candidate actions.
arXiv:2606.28900v2 Announce Type: replace Abstract: Doctor agents are moving beyond single-turn answer generation toward evolving clinical decision systems that acquire evidence within episodes and reuse experience acros…
arXiv:2606.29354v2 Announce Type: replace Abstract: Chain-of-Thought (CoT) improves large language models (LLMs) on difficult reasoning tasks, but it often incurs long natural-language rationales that are poorly aligned…
arXiv:2607.08964v3 Announce Type: replace Abstract: AI agents have become capable of autonomously completing short, well-specified tasks.
arXiv:2607.12747v2 Announce Type: replace Abstract: Failure attribution for LLM-based agentic systems, i.e., identifying which steps in a failure trajectory caused the task to fail, is critical for debugging and improvin…
arXiv:2607.24162v3 Announce Type: replace Abstract: Workflow search pays for complete quality observations, whose execution cost changes as reusable prefixes accumulate.
arXiv:2607.25292v3 Announce Type: replace Abstract: Silicon sampling uses language models as proxies for human survey respondents, treating each model call as an independent draw from the persona's response distribution.
arXiv:2607.28103v2 Announce Type: replace Abstract: Memory-augmented LLM-based agents are vulnerable to memory injection attacks: Agents may retrieve poisoned memory from attackers, which diverts their behavior from init…
arXiv:2608.01008v2 Announce Type: replace Abstract: Multimodal large language models (MLLMs) can memorize and disclose sensitive information, motivating machine unlearning to remove designated knowledge while preserving…
arXiv:2608.01805v2 Announce Type: replace Abstract: LLM multi-agent systems suffer from Correctness Collapse, where high task-level accuracy conceals severe process-level failures.
arXiv:2608.01822v2 Announce Type: replace Abstract: Training LLM-based search agents requires high-quality search data: tasks that demand genuine multi-hop retrieval and trajectories that use search tools effectively.
arXiv:2608.03874v2 Announce Type: replace Abstract: Modern agent frameworks equip large language models with external skill libraries to solve complex tasks.
arXiv:2608.05141v2 Announce Type: replace Abstract: Context lengths of language models (LMs) have dramatically increased, driven by the demands for in-context learning, self-improvement, and long-horizon agentic workflow…
arXiv:2608.06891v2 Announce Type: replace Abstract: Agent skills provide reusable knowledge that helps agents solve specialized tasks.
arXiv:2608.08960v2 Announce Type: replace Abstract: Multi-step language-model agents repeatedly process growing interaction histories, leading to substantial context costs.
arXiv:2608.09248v3 Announce Type: replace Abstract: Skill-based LLM agents select reusable procedures from external libraries to solve complex tasks, yet their routing decisions rely primarily on task descriptions, verba…
arXiv:2608.11977v2 Announce Type: replace Abstract: Tool-using LLM agents are typically developed and post-trained in controlled environments with reliable tools, but deployment exposes them to tool failures, API and sch…
arXiv:2608.13618v2 Announce Type: replace Abstract: Clinical algorithms can perform differently across patient groups, a concern that grows as these algorithms increasingly take the form of artificial intelligence (AI) m…
arXiv:2608.19729v2 Announce Type: replace Abstract: Vision-language-model-based embodied agents can complete instructed tasks but often violate safety constraints in the process, a problem recently framed as interactive…
arXiv:2608.19974v2 Announce Type: replace Abstract: LLM agents in financial markets may cite rules yet still submit orders that violate executable constraints or misread surveillance evidence.
arXiv:2608.21712v3 Announce Type: replace Abstract: Transformer architectures for clinical prediction from electronic health records (EHRs) often require costly manual tuning and may vary across hospitals and tasks.
arXiv:2608.22971v2 Announce Type: replace Abstract: Embodied AI has emerged as a key paradigm for autonomous systems operating in complex physical environments.
arXiv:2608.24569v2 Announce Type: replace Abstract: Large language model (LLM) agents build on one another's work through summaries, plans, and other intermediate artifacts.
arXiv:2608.28281v2 Announce Type: replace Abstract: Loop Engineering is emerging as a practice for organizing development work around coding agents.
arXiv:2608.28399v2 Announce Type: replace Abstract: In financial markets, a sequential policy that reacts systematically to price movements may become predictable to other market participants.
arXiv:2608.28553v4 Announce Type: replace Abstract: Plugin-based agents assemble capabilities at runtime, and the spatiotemporal-composability calculus proves a reversibility guarantee for this assembly.
arXiv:2609.09448v2 Announce Type: replace Abstract: As agentic systems getting adopted rapidly in safety critical applications, it is vital to measure the confidence associated with the agentic actions.
arXiv:2609.13667v2 Announce Type: replace Abstract: Geospatial agents are increasingly expected to support recurring and evolving analytical tasks rather than execute isolated workflows.
arXiv:2308.12241v2 Announce Type: replace-cross Abstract: Recently, the fast development of Large Language Models (LLMs) such as ChatGPT has significantly advanced NLP tasks by enhancing the capabilities of conversationa…
arXiv:2310.14040v2 Announce Type: replace-cross Abstract: Diffusion models have shown promising results for a wide range of generative tasks with continuous data, such as image and audio synthesis.
arXiv:2402.03694v3 Announce Type: replace-cross Abstract: Network traffic analysis in cloud and internet service provider (ISP) networks increasingly relies on machine learning (ML) models, as encryption and service cons…
arXiv:2502.04356v2 Announce Type: replace-cross Abstract: In response to the success of proprietary Large Language Models (LLMs), there is a growing interest in developing open, non-proprietary LLMs and AI foundation mod…
arXiv:2503.04940v3 Announce Type: replace-cross Abstract: Emergent Language (EL) focuses on the emergence of communication among artificial agents.
arXiv:2503.14555v2 Announce Type: replace-cross Abstract: Traditional multi-agent reinforcement learning (MARL) systems can develop cooperative strategies through repeated interactions.
arXiv:2505.08814v4 Announce Type: replace-cross Abstract: Deep neural networks (DNNs) play a crucial role in the field of artificial intelligence, and their security-related testing has been a prominent research focus.
arXiv:2506.10946v3 Announce Type: replace-cross Abstract: Unlearning large language models (LLMs) is important due to copyright and privacy concerns.