Knowledge catalogue
arXiv:2609.01608v1 Announce Type: cross Abstract: Black-box optimization problems remain challenging because of large, weakly structured, and high-dimensional search spaces. Existing methods often suf
arXiv:2609.00749v1 Announce Type: new Abstract: Long-horizon large language model (LLM) agents require context assembly: the runtime must decide what to include in each prompt, in what order, and when
arXiv:2602.18493v2 Announce Type: replace-cross Abstract: Long-context LLMs and Retrieval-Augmented Generation defer state tracking and evidence consolidation to query time, which is brittle when fact
arXiv:2609.00455v1 Announce Type: new Abstract: Large language models (LLMs) are being used as policies for autonomous decision-making and planning in many domains. Despite their strong reasoning capa
arXiv:2608.30760v1 Announce Type: new Abstract: Recent studies have shown that multimodal large language models (MLLMs) can serve as embodied agents, translating language instructions and visual obser
arXiv:2608.23651v1 Announce Type: cross Abstract: Agent harnesses record a failed tool call and its error message in the transcript and ask the model to continue, on the assumption that the error is c
arXiv:2602.10863v2 Announce Type: replace-cross Abstract: Long-horizon reinforcement learning for information seeking agents remains difficult because terminal rewards reveal whether the final answer
arXiv:2603.28200v2 Announce Type: replace-cross Abstract: Guiding collective motion in biological groups is a fundamental challenge in understanding social interaction rules. In this study, we propose
arXiv:2608.20797v1 Announce Type: new Abstract: Evaluating language-guided mobile agents has recently shifted from rule-based to model-based approaches to achieve scalable and automated assessments. H
arXiv:2607.11818v2 Announce Type: replace-cross Abstract: We introduce MM-ToolSandBox, a benchmark and evaluation framework for visually grounded tool-calling agents. The framework provides a stateful
arXiv:2606.18847v2 Announce Type: replace Abstract: To assist humans over extended periods in real homes, embodied agents must remember user routines, world states, and past interactions. Existing lon
Home page for humans: https://parker-lambert-sandbox.com/robot-world/ Home page for AI agents: https://parker-lambert-sandbox.com/robot-world/start/ If you're a human, you can watch, but not interact:
arXiv:2608.19662v1 Announce Type: new Abstract: Agentic language models repeatedly encode tool and skill schemas that recur across requests in different combinations and orders, preventing standard pr
arXiv:2608.19729v1 Announce Type: new Abstract: Vision-language-model-based embodied agents can complete instructed tasks but often violate safety constraints in the process, a problem recently framed
arXiv:2607.13854v2 Announce Type: replace Abstract: Multimodal agents that think with images iteratively manipulate visual evidence and invoke tools across many steps. Existing reinforcement learning
arXiv:2601.18305v2 Announce Type: replace Abstract: Despite numerous Graphical User Interface (GUI) agents claiming to automate user interaction tasks, to date, few achieve satisfactory interaction ca
arXiv:2608.17034v1 Announce Type: new Abstract: Post-training can unlock new capabilities and improve performance on specialized tasks, but sometimes at the cost of catastrophic forgetting in other do
arXiv:2608.17684v1 Announce Type: new Abstract: Self-evolving agents turn experience into reusable skills, workflows, or memories, but post-evolution accuracy alone does not show whether learned behav
arXiv:2601.10161v3 Announce Type: replace-cross Abstract: Named Entity Recognition (NER) and Personally Identifiable Information (PII) anonymization are critical tasks in Natural Language Processing (
arXiv:2608.16068v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as agents that rely on system prompts to use tools and complete tasks. Such deployments impose
arXiv:2608.15008v1 Announce Type: new Abstract: Memory is becoming core infrastructure for long-horizon LLM agents, yet existing evaluations offer limited guidance on which memory substrate, namely th
arXiv:2608.14642v1 Announce Type: new Abstract: Reinforcement Learning (RL) agents trained on a single reward signal exploit the gap between the designed reward and the intended behavior. This is part
arXiv:2608.14109v1 Announce Type: new Abstract: Autonomous LLM agents are increasingly deployed in complex real-world workflows, yet they remain vulnerable to runtime behavioral drift, a silent deviat
arXiv:2608.12764v1 Announce Type: cross Abstract: Deep search agents operate over trajectories spanning dozens of steps, yet standard reinforcement learning provides only a single outcome reward per t
arXiv:2608.12877v1 Announce Type: new Abstract: Multi-hop fact verification, which verifies claims by reasoning over multiple pieces of evidence, is critical for combating misinformation on social med
our outbound harness is focused on delivering the best economics we can, we're continuing to push on how our agents work to get another 90%+ cost savings for customers great talk by @hwchase17 and @He
arXiv:2608.11350v1 Announce Type: new Abstract: Embodied agents are increasingly built as systems around foundation models, where performance depends not only on model weights but also on the skills,
arXiv:2607.11175v2 Announce Type: replace Abstract: The growing ability of large language models and vision-language models to jointly interpret and reason over images and text is reshaping medical im
arXiv:2510.04399v3 Announce Type: replace Abstract: We develop a learning-theoretic framework for analyzing self-improving agents by decomposing self-modification into five axes. Within this framework
arXiv:2608.07775v1 Announce Type: new Abstract: Mobile agents have achieved promising results on clean online benchmarks such as AndroidWorld, yet their performance often degrades sharply in real-worl
arXiv:2608.08392v1 Announce Type: new Abstract: Large language models are increasingly deployed as autonomous agents that interact with the web through browsers. While recent progress has been driven
arXiv:2608.08036v1 Announce Type: new Abstract: Frontier agentic models are increasingly deployed as high-level planners for long-horizon embodied tasks. Existing robotic benchmarks have advanced long
arXiv:2608.06735v1 Announce Type: new Abstract: Reinforcement learning (RL) has achieved strong results in improving large language models (LLMs) on tasks with stationary, verifiable rewards, such as
arXiv:2608.06968v1 Announce Type: cross Abstract: Language-model agents act on state encodings of their environment, yet these are treated as interchangeable interfaces. Using pretrained language mode
arXiv:2608.06663v1 Announce Type: new Abstract: Frontier language models solve reasoning problems in a single forward pass that would have been research contributions years ago, yet fail at multi-hour
arXiv:2608.05199v1 Announce Type: cross Abstract: Autonomous security agents operate as staged pipelines, such as classifying network traffic and then attributing attacks to a specific technique. Spli
arXiv:2608.05587v1 Announce Type: new Abstract: Autonomous mobile GUI agents require accurate action reflection for reliable long-horizon execution. Existing approaches rely on open-ended multimodal r
arXiv:2608.05102v1 Announce Type: new Abstract: Long-horizon search agents must make multiple sequential actions (steps) to search, retrieve, verify, and integrate evidence to reach a final answer. Ho
arXiv:2608.04574v1 Announce Type: new Abstract: Memory-augmented VLM agents act on persistent spatial knowledge, yet that knowledge silently goes stale as the environment changes. We ask what happens
arXiv:2608.03874v1 Announce Type: new Abstract: Modern agent frameworks equip large language models with external skill libraries to solve complex tasks. However, it remains unclear whether these syst
arXiv:2608.02670v1 Announce Type: cross Abstract: Coding agents increasingly run inside organizations whose security controls (scoped credentials, restricted egress, read-only filesystems, non-root ex
arXiv:2607.28048v2 Announce Type: replace Abstract: Skill-based prompting has become a practical mechanism for improving large language model (LLM) agents, yet existing skill acquisition methods often
arXiv:2608.00832v1 Announce Type: new Abstract: Structured plan-generation agents are often evaluated as if a plan has quality in isolation, yet many realistic planning tasks require asking how a cand
arXiv:2608.01358v1 Announce Type: new Abstract: Search-augmented large language model agents are increasingly capable of solving knowledge-intensive tasks, but their behavior when a multi-hop question
Just for reference, from what I observed in my Using Local Coding Agents blog article last month: https://x.com/rasbt/status/2070518167399698490?s=20 'I tried to analyze why Claude Code uses more toke
arXiv:2607.25765v1 Announce Type: new Abstract: Enterprise agents often need to integrate heterogeneous knowledge sources: documents for narrative facts, tables for computation, and dependency graphs
arXiv:2607.23332v1 Announce Type: new Abstract: Creating a reusable tool is an investment: an agent pays a fixed cost now in exchange for the potential of future reuse. Therefore, a user should prefer
arXiv:2607.22962v1 Announce Type: new Abstract: LLM agents that operate over many turns accumulate facts in an external memory store and reuse them as premises for downstream reasoning. A hallucinated
arXiv:2607.15845v2 Announce Type: replace Abstract: Workflow generation in visual creation systems such as ComfyUI demands not only syntactic accuracy but also expert-level reasoning over modular comp
arXiv:2607.22947v1 Announce Type: new Abstract: A formal model enables verifying reachability, localizing an outage, or anticipating the blast radius of a change. Yet, virtually no production network
arXiv:2607.23870v1 Announce Type: cross Abstract: Smart-city airspace is transforming Uncrewed Aerial Vehicles (UAVs) from passive sensing platforms into cyber-physical decision makers that must follo
arXiv:2508.00288v5 Announce Type: replace-cross Abstract: Aerial navigation is a fundamental yet underexplored capability in embodied intelligence, enabling agents to operate in large-scale, unstructu
arXiv:2607.22868v1 Announce Type: new Abstract: Runtime guardrails act before irreversible tool calls, but their guarantees depend on what policy state is representable, what a judge observes, and whe
Very cool paper from Microsoft. The idea is to train agents on replayed teacher trajectories instead of live environment rollouts. On-policy distillation for agentic tasks is expensive because every u
arXiv:2607.20645v1 Announce Type: cross Abstract: We introduce Frontier Financial Judgement, a challenging new benchmark developed in collaboration with professional equity analysts to assess agents'
arXiv:2607.20482v1 Announce Type: new Abstract: Recent advances in large language models have enabled web agents to autonomously execute complex tasks. In practice, users frequently provide underspeci
arXiv:2607.19865v1 Announce Type: new Abstract: As autonomous agents rapidly evolve, their ability to reliably manipulate ubiquitous digital documents has become critical for enabling general-purpose
Together, Motorway and AWS built an end-to-end evaluation pipeline that reduced incorrect results from 1 in 8 queries to 1 in 50 and cut issue detection time from few hours to few minutes. The pipelin
AI Teammates are agentic AI on Amazon Bedrock, and few engineering organizations run them in production at the scale that monday.com does. Nine in ten Builders use AI coding tools every month, up from
This incident is deeply concerning. AI agents are willing to cheat and deceive to achieve misaligned and unintended goals, behaviours which have been demonstrated in controlled tests for months. Now,