CompanyAnthropic8 recent entries22 Sept 2026GameReplica: A Benchmark for Black-Box Visual Game Replication by Vision-Language AgentsarXiv:2609.22308v1 Announce Type: new Abstract: Coding-agent benchmarks usually evaluate implementation after the target behavior has been specified in text, code, or demonstrations. Existing research→29 Sept 2026Timeline-Bench: Evaluating Agents on Realistic Video-Editing Tasks, from Raw Footage to Final CutarXiv: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
CompanyOpenAI2 recent entries15 Apr 2026Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent WorkloadsarXiv:2604.12301v1 Announce Type: cross Abstract: We present a systematic measurement study of seven tactics for reducing cloud LLM token usage when a small local model can act as a triage layer in fr→27 Jul 2026Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and ImagesarXiv:2607.21672v1 Announce Type: cross Abstract: Long source-code contexts consume many text tokens, motivating the proposal to render code as images for vision-language models. Recent work asks whet
CompanyGoogle4 recent entries27 Jul 2026Pixels for Programs? A Cross-Provider Case Study of Input-Token Accounting for Source Code as Text and ImagesarXiv:2607.21672v1 Announce Type: cross Abstract: Long source-code contexts consume many text tokens, motivating the proposal to render code as images for vision-language models. Recent work asks whet→2 Sept 2026Dr. Claw: An AI Scientist Workspace for Vibe ResearcharXiv:2609.00365v1 Announce Type: new Abstract: Command-line coding agents (e.g., Claude Code, Gemini CLI) can already read and write files and sustain long sessions, yet end-to-end research still fra→30 Sept 2026Code4Scene: Benchmarking Coding Agents for Constructing and Editing 3D ScenesarXiv:2609.36777v1 Announce Type: new Abstract: Frontier coding agents can now write and execute code that authors 3D environments, but whether they reliably understand 3D structure and precisely cont→15 Oct 2026Do Theorem Provers Need Theorem-Proving Agents? mini-Lean-agent: A Coding-Agent Baseline for LeanarXiv:2610.17331v1 Announce Type: new Abstract: General-purpose coding agents use standard shell and file interactions, yet formal theorem-proving agents often rely on specialized, ad-hoc tooling. Thi
CompanyMeta2 recent entries1 Oct 2026RankEvolve: A Reliable Multi-Agent Auto-Research Harness for Evolving Ranking ModelsarXiv: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→15 Oct 2026Trace-to-Architecture: Capability Bottleneck Diagnosis for Harness RevisionarXiv:2610.16725v1 Announce Type: new Abstract: Improving an LLM agent requires knowing what to change when it fails. Similar failures can require different fixes, and resolving one problem can expose
CompanyDeepSeek2 recent entries26 Aug 2026The Empire, Long Divided, Must Unite: Architectural Convergence in Three LLM Agent HarnessesarXiv:2608.23953v1 Announce Type: cross Abstract: An agent harness is what turns a language model into an autonomous agent: the surrounding code that builds the model's context, mediates its tools, ru→2 Sept 2026Harness-of-Harness: Multi-Day Autonomous Software Development with Continual ImprovementarXiv:2609.01481v1 Announce Type: new Abstract: This paper studies autonomous software development, in which LLM-based coding agents transform high-level requirements into complete, functional, and us