3,698 items tracked: 33 reported by two or more outlets, the rest by a single source. Most-corroborated first.
Ai2 joined COLM 2026 to share advances in open language models, training infrastructure, and AI for science, including Olmo Hybrid, Asta, and Bolmo, while connecting with the broader research community.
Multi-Agent swarms are important for two reasons: They are probably much faster and somewhat more capable than single agents (Capability) Multi-agent alignment is a different beast than single-agent alignment (Propensity…
arXiv:2610.11732v2 Announce Type: replace Abstract: Large language model (LLM) agents for portfolio management learn from experience: they credit each experience in their memory with the outcome of the decisions that use…
arXiv:2610.11773v2 Announce Type: replace Abstract: Guard models are increasingly used to safeguard LLM-based agents, primarily by identifying actions that agents are forbidden to perform.
arXiv:2610.10787v2 Announce Type: replace-cross Abstract: Language models trained with long-horizon agentic reinforcement learning can generalize knowledge through reasoning, express precise actions, and pursue goals ove…
arXiv:2610.11060v2 Announce Type: replace-cross Abstract: World-action models have recently improved autonomous driving by jointly learning future scene prediction and trajectory generation.
arXiv:2610.11542v3 Announce Type: replace-cross Abstract: Multi-agent LLM systems negotiating with a stateful counterpart waste model calls in three ways: polite loops that never meet the counterpart's hidden acceptance…
arXiv:2610.11647v2 Announce Type: replace-cross Abstract: Coding agents are extended with agent skills, directories whose SKILL.md tells the model when and how to perform a task.
arXiv:2507.14897v3 Announce Type: replace Abstract: Methods to build LLM agents have evolved from prompt engineering and supervised finetuning to agentic reinforcement learning (agentic RL).
arXiv:2603.23406v4 Announce Type: replace Abstract: Generative agent societies simulate people with assigned roles, preferences and relationships.
arXiv:2610.10549v1 Announce Type: new Abstract: Tool-calling agents have become central to enterprise AI, yet training and evaluating them at scale remains severely constrained due to business and legal restrictions on e…
arXiv:2610.10590v1 Announce Type: new Abstract: Tool-using agents repeatedly carry observations whose useful content can be much smaller than their original payload.
arXiv:2610.10611v1 Announce Type: new Abstract: Agentic AI systems can improve by searching longer, receiving additional support, or modifying how they propose and verify outputs.
arXiv:2610.10629v1 Announce Type: new Abstract: Self-improving LLM agents can adapt a credit pipeline to a changed rule, but an agent that rewrites itself destroys the artefact a supervisor reviews: a named change, a rec…
arXiv:2610.10635v1 Announce Type: new Abstract: Aerial vision-and-language navigation (VLN) agents are typically trained on detail-rich, trajectory-aligned commands, whereas users issue short, intent-driven instructions;…
arXiv:2610.10786v1 Announce Type: new Abstract: Planning is increasingly important for long-horizon agents, where successful execution requires coordinating subgoals, tool use, and intermediate outcomes over many steps.
arXiv:2610.10833v1 Announce Type: new Abstract: We study whether small LLM agents can operate effectively under explicit wall-clock time budgets by both respecting the allocated runtime and using available time productiv…
arXiv:2610.10942v1 Announce Type: new Abstract: Reinforcement learning environments are now a primary lever for improving large language model (LLM) capabilities in post-training, yet most agentic benchmarks remain stati…
arXiv:2610.11007v1 Announce Type: new Abstract: At the start of every session, LLM agents load a fixed context file, such as $\texttt{AGENTS.md}$.
arXiv:2610.11050v1 Announce Type: new Abstract: Computer-use agents are capable of completing complex tasks, increasing the use of automatic judges to determine success, either for training or for evaluation without huma…
arXiv:2610.11188v1 Announce Type: new Abstract: Persistent memory can improve personalization in LLM agents but can also induce sycophancy and cross-domain leakage.
arXiv:2610.11253v1 Announce Type: new Abstract: Large language model agents are being increasingly deployed as autonomous scientists, designing experiments and inferring mechanistic world models with minimal human oversi…
arXiv:2610.11299v1 Announce Type: new Abstract: Voice agents are converging on a collaboration pattern: a full-duplex interaction model stays on the live channel as the entry to the conversation, while search, reasoning,…
arXiv:2610.11312v1 Announce Type: new Abstract: Large-scale construction of medical vision-language model (VLM) benchmarks is increasingly feasible with richly annotated imaging datasets and large language models (LLMs),…
arXiv:2610.11328v1 Announce Type: new Abstract: Advances in foundation models are driving efforts to introduce agents to assist people in the physical world.
arXiv:2610.11334v1 Announce Type: new Abstract: In LLM-based agent systems, failures can originate from early steps whose effects propagate through subsequent interactions, making their origins difficult to identify.
arXiv:2610.11345v1 Announce Type: new Abstract: Self-evolving LLM agents promise to improve autonomously through continual interaction and learning, reducing their dependence on manually curated supervision.
arXiv:2610.11358v1 Announce Type: new Abstract: Cross-model KV-cache reuse remains a key challenge in modern LLM serving.
arXiv:2610.11384v1 Announce Type: new Abstract: Reinforcement learning is commonly used to train language agents in interactive environments, but cannot be directly applied when rewards are unavailable.
arXiv:2610.11450v1 Announce Type: new Abstract: We study how a coding agent learns across a sequence of abstract reasoning tasks.
arXiv:2610.11464v1 Announce Type: new Abstract: We changed the agent: did it actually get better?
arXiv:2610.11552v1 Announce Type: new Abstract: Large language model agents can invoke tools fluently, but enterprise workflows demand more than selecting the right tools: actions must strictly comply with organizational…
arXiv:2610.11561v1 Announce Type: new Abstract: LLM-based agents now interact with their environments continuously, shaped by such organizational channels as user instructions, peer messages, and long-term memory.
arXiv:2610.11573v1 Announce Type: new Abstract: The memory capabilities of Large Language Models (LLMs) have garnered increasing attention recently.
arXiv:2610.11600v1 Announce Type: new Abstract: LLM-based multi-agent systems (MASs) are increasingly used to solve complex tasks through coordinated reasoning, tool use, and interaction with external resources.
arXiv:2610.11613v1 Announce Type: new Abstract: An agent can complete a task without improving how it works.
arXiv:2610.11707v1 Announce Type: new Abstract: Memory-augmented mobile GUI agents store successful execution trajectories and reuse them in later tasks, but a stored trajectory rarely matches a new task exactly.
arXiv:2610.11754v1 Announce Type: new Abstract: Some defects in an AI-generated study can be identified from its artifacts; others require knowledge of what was approved before execution.
arXiv:2610.11794v1 Announce Type: new Abstract: Learning to act in unfamiliar environments requires agents to infer how the world works and revise that understanding as new evidence arrives.
arXiv:2610.12061v1 Announce Type: new Abstract: Large language model (LLM)-based agents have demonstrated strong capabilities on complex tasks.
arXiv:2610.12086v1 Announce Type: new Abstract: LLM-based program evolution relies on evaluation feedback to guide the iterative search for high-performing programs.
arXiv:2610.12124v1 Announce Type: new Abstract: The evolution of Large Language Model agents from single-task execution to long-term autonomous operation highlights the critical challenge of transforming continuous exper…
arXiv:2610.12134v1 Announce Type: new Abstract: Knee osteoarthritis (KOA) progression prediction can support patient monitoring, requiring the integration of multimodal data and multidomain expertise.
arXiv:2610.12176v1 Announce Type: new Abstract: Recursive self-improvement (RSI) of a model on non-verifiable tasks, such as open-ended research, faces a supervision bottleneck when its outputs exceed what even human exp…
arXiv:2610.12292v1 Announce Type: new Abstract: A typed decision model reads a piece of text and returns a probability over caller-defined options, each with a short written definition, generating no text.
arXiv:2610.12375v1 Announce Type: new Abstract: Agents are deployed in applications from trip planners and stock trading to IT incident triage.
arXiv:2610.12436v1 Announce Type: new Abstract: AI agents can now conduct real-world cyberattacks, scale up capabilities with the number of agents, and collectively pursue misaligned goals to obtain rewards.
arXiv:2610.10608v1 Announce Type: cross Abstract: Security operations centers (SOCs) must triage large volumes of alerts, most of which are benign, while missed attacks can remain uninvestigated.
arXiv:2610.10610v1 Announce Type: cross Abstract: Repository benchmarks (e.g., SWE-bench) for coding agents often assume that lines of code edited can predict task difficulty, but such datasets' poor control over code an…
arXiv:2610.10619v1 Announce Type: cross Abstract: Large language model (LLM) agents are rapidly reshaping software engineering, accompanied by an explosion of new code benchmarks.