Knowledge catalogue
arXiv:2604.14858v2 Announce Type: replace Abstract: As agent systems move into increasingly diverse execution settings, trajectory-level safety evaluation and diagnosis require benchmarks that evolve
arXiv:2606.31909v1 Announce Type: new Abstract: In this work, we study Compositional Dexterous Functional Object Manipulation (CD-FOM): tasks such as aiming and actuating a spray bottle on a plant or
arXiv:2606.31179v1 Announce Type: new Abstract: As AI agents become increasingly capable of complex, long-horizon reasoning, rigorous and holistic evaluation is essential for measuring progress toward
arXiv:2605.28916v1 Announce Type: cross Abstract: We report a comparison of two state-of-the-art agentic AI systems, Claude Code (Anthropic) and Codex (OpenAI), tasked with autonomously executing a si
arXiv:2607.21557v1 Announce Type: new Abstract: Modern AI agents rely on elaborate inference harnesses such as Claude Code, Codex, and OpenClaw to drive multi-turn reasoning, tool use, and access to e
arXiv:2605.23131v1 Announce Type: new Abstract: In this note, I would like to share a small research moment where Codex helped me find the right way to adapt rare switching to the private setting. The
arXiv:2605.23904v1 Announce Type: new Abstract: Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning
arXiv:2604.11003v1 Announce Type: new Abstract: Agentic data science (ADS) pipelines have grown rapidly in both capability and adoption, with systems such as OpenAI Codex now able to directly analyze
arXiv:2610.11559v1 Announce Type: cross Abstract: Coding assistants such as Claude Code and Codex have become a major application of LLM agents, yet existing benchmarks remain far from real-world use,
arXiv:2610.12183v1 Announce Type: cross Abstract: Black-box optimization (BBO) arises in many scientific and engineering problems where objective evaluations are expensive and limited. Recent large la
arXiv:2610.09944v2 Announce Type: replace Abstract: An essential control of AI agents is their ability to manage runtime. This ability requires a sense of time-awareness, to predict and estimate wall-
arXiv:2603.08993v2 Announce Type: replace-cross Abstract: System prompts for LLM-based coding agents are software artifacts that govern agent behavior, yet lack the testing infrastructure applied to c
arXiv:2610.10961v1 Announce Type: cross Abstract: Coding agents increasingly share a workstation while drawing on separate providers and subscription allowances. A second agent can inspect a completed
arXiv:2610.04838v2 Announce Type: replace Abstract: As coding agents take on long-horizon software evolution tasks spanning multiple files and stages, longer execution trajectories introduce two coupl
arXiv:2610.06914v1 Announce Type: new Abstract: Text2Dashboard is a DataBrain-specific prototype that turns natural-language analytic requests into inspectable dashboards. An installable Codex plugin
arXiv:2609.38983v1 Announce Type: cross Abstract: Modern AI coding-agent harnesses (Claude Code, Codex CLI, Cursor) rest their security boundary on a largely unexamined assumption: that the action A a
arXiv:2609.38372v1 Announce Type: new Abstract: A harness is the code around a language-model agent that organizes prompts, calls tools, manages context, and controls execution. As models grow stronge
arXiv:2609.38912v1 Announce Type: new Abstract: Agent harnesses govern how large language models (LLMs) gather context, invoke tools, verify results, preserve state, and terminate, largely affecting a
arXiv:2609.38948v1 Announce Type: cross Abstract: Frontier models excel at many digital benchmarks, yet their ability to drive a real car, an everyday human skill, remains largely untested. We present
arXiv:2609.38345v1 Announce Type: cross Abstract: Multi-agent coding systems are designed to tackle complex software engineering tasks through collaboration. However, existing evaluations typically as
arXiv:2609.40118v1 Announce Type: new Abstract: As LLM capabilities advance, agents are tackling increasingly complex tasks over longer horizons. Their growing interaction histories make memory compac
arXiv:2609.39551v1 Announce Type: new Abstract: Auto-research agents, LLM systems that propose, implement, train, and evaluate model changes across iterations, promise to automate applied ML's experim
arXiv:2609.35501v1 Announce Type: cross Abstract: Recent agentic symbolic regression approaches increasingly rely on large language models to analyze data, select scientific operations, and refine hyp
arXiv:2609.35143v1 Announce Type: new Abstract: AI agents increasingly carry out long-horizon professional work, but their evaluations rarely require a finished creative deliverable. To this end, we i
arXiv:2609.20835v1 Announce Type: new Abstract: Background: The Voynich Manuscript is a fifteenth-century codex written in an unknown script whose content remains undeciphered. Previous studies sugges
arXiv:2608.26130v1 Announce Type: new Abstract: Coding agents built on large language models (LLMs), such as Claude Code, Cursor, OpenAI Codex, GitHub Copilot, and Aider, receive tool responses that r
arXiv:2607.18064v2 Announce Type: replace-cross Abstract: Coding agents can now be left alone to improve software against a score. In this pattern--recently popularized as 'autoresearch'--the agent re
arXiv:2608.14396v1 Announce Type: cross Abstract: The alternating direction method of multipliers (ADMM), as a landmark algorithm, has attracted tremendous research attention and extensive practical a
arXiv:2608.07555v1 Announce Type: new Abstract: Coding agents such as Claude Code and Codex close the software loop: a main agent manages the loop, subagents analyze and execute, tools do the work. We
arXiv:2608.02642v1 Announce Type: cross Abstract: Accelerating scientific discovery is among the most consequential applications of AI, and computational biomolecular simulation stands out as a partic
arXiv:2608.00101v1 Announce Type: cross Abstract: AI coding agents like GitHub Copilot, Claude Code, and Codex interleave multi-step LLM inference with tool execution, creating a workload different fr
arXiv:2606.08091v1 Announce Type: new Abstract: Recent agent frameworks such as Claude Code, Codex, and OpenClaw are strong at tool use and orchestration, but whether they can handle long video genera
arXiv:2606.00288v1 Announce Type: new Abstract: Large language models are undergoing a transition from model technology to system technology. As developers use Codex, Claude Code, AutoGPT, and related
arXiv:2605.26047v1 Announce Type: new Abstract: AI coding scaffolds like Claude Code and Codex use extit{retrying}: blocking actions flagged as risky and continuing the trajectory. We study retrying f
arXiv:2605.13625v1 Announce Type: new Abstract: Autonomous agents such as Claude Code and Codex now operate for hours or even days. Understanding their runtime behavior has become critical for downstr
arXiv:2610.13075v1 Announce Type: new Abstract: Corpus-level long-context reasoning requires agents to acquire and integrate evidence across document collections that exceed their context windows. Exi
arXiv:2610.12569v1 Announce Type: new Abstract: Static coding benchmarks are fixed at release. Over time their tasks leak into training data, and stronger agents eventually saturate them. We argue tha
arXiv:2610.03153v1 Announce Type: cross Abstract: Workspace agents combine large language models with execution harnesses to perform stateful, multi-step tasks that access or modify external resources
arXiv:2610.02569v1 Announce Type: cross Abstract: Coding agents have become increasingly long-horizon, autonomous, reliant on general-purpose shell and maintain their own persistent memory for self-im
arXiv:2609.31318v1 Announce Type: cross Abstract: AI agents combine language models with external data and tools that can modify files, call APIs, or execute code. Security failures can arise when adv
arXiv:2609.26779v1 Announce Type: cross Abstract: Agents often work on complex problems that require millions of tokens of context, which necessitates compacting across sessions due to limited context
arXiv:2609.18460v1 Announce Type: new Abstract: How does a multi-agent system evolve from a local deviation into collective loss of control? We propose an epidemic explanation organized around acciden
arXiv:2608.22981v1 Announce Type: new Abstract: Knowledge graphs are often accompanied by ontological class hierarchies that encode valuable semantic information, yet many link prediction methods eith
arXiv:2607.13085v1 Announce Type: cross Abstract: Recent autonomous penetration testing papers report high benchmark scores while adding multi-component security harnesses around frontier LLMs. Becaus
arXiv:2607.08255v1 Announce Type: new Abstract: Large language models increasingly serve as teachers generating training data for smaller students. Prior multi-teacher knowledge distillation methods m
arXiv:2607.03833v1 Announce Type: cross Abstract: While Large Language Models (LLMs) have achieved remarkable success in Text-to-SQL tasks, their deployment in real-world environments is hindered by l
arXiv:2606.24429v1 Announce Type: cross Abstract: Generative AI coding agents are entering the open-source supply chain, yet their diverse and often invisible traces leave their prevalence poorly unde
arXiv:2606.11447v1 Announce Type: new Abstract: Recent anecdotal evidence suggests that AI coding agents can reproduce published findings when provided with original data and code; yet systematic eval
arXiv:2606.11456v1 Announce Type: cross Abstract: The deployment of LLM-based agents in scientific analysis raises opposing concerns: that agents may reduce methodological diversity, or that they may
arXiv:2606.11976v1 Announce Type: cross Abstract: Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue. Most AI agents explore repos
arXiv:2606.10106v1 Announce Type: cross Abstract: The term agent harness now circulates widely in software engineering with generative artificial intelligence. It names the layer that wraps a language
arXiv:2604.05333v3 Announce Type: replace Abstract: Modern LLM agents increasingly rely on reusable skills, and as they interact with personal applications, web browsers, and other interfaces, skill l
arXiv:2605.19156v1 Announce Type: new Abstract: Recent auto-research systems can produce complete papers, but feasibility is not the same as quality, and the field still lacks a systematic study of ho
arXiv:2511.21654v2 Announce Type: replace Abstract: We introduce EvilGenie, a benchmark for reward hacking in programming settings. We source problems from LiveCodeBench and create an environment in w
arXiv:2605.17986v1 Announce Type: cross Abstract: AI agents such as OpenClaw are increasingly deployed in local workflows with access to external tools. This creates indirect prompt-injection (IPI) ri
arXiv:2605.18583v1 Announce Type: cross Abstract: Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than a
arXiv:2610.05367v1 Announce Type: cross Abstract: Proof auto-formalization translates natural-language (NL) theorems and proofs into a formal language (FL) such as Lean, enabling mechanical verificati
arXiv:2610.00917v1 Announce Type: new Abstract: Choosing an agent system means choosing both a language model and the harness through which it acts. We ask whether a strong model, harness, or pairing
arXiv:2610.00912v1 Announce Type: new Abstract: Large language models can translate business descriptions into optimization models, but executable code may misrepresent constraints or objectives. A so
arXiv:2609.35841v1 Announce Type: cross Abstract: Mutation testing evaluates test-suite adequacy by injecting synthetic faults into program code. However, traditional rule-based tools often generate l