arXiv AI
Jul 14
What Context Does a Coding Agent Actually Need to Act?
arXiv:2607. 09691v1 Announce Type: cross Abstract: A modern coding agent can hold an entire repository in its context window.
Does a Language Server Save Tokens for Coding Agents? A Measurement Methodology and Preliminary Study
arXiv:2608. 13568v1 Announce Type: cross Abstract: Coding agents spend most of their context budget on retrieval.
Related stories
arXiv AI
Jul 8
RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications
arXiv:2607. 06411v1 Announce Type: cross Abstract: Developers increasingly delegate real maintenance work to product-grade coding agents, and many state tasks in their native language, in the style of a customer request rather than a curated English issue.
Hugging Face Trending Papers
Aug 11
Actions Speak Louder than Words: Measuring Cross-Lingual Policy Retention in Tool-Using Agents
When a tool-using agent is given the same task in a different language, does it still take the same steps? Multilingual evaluation rarely asks: it compares final answers and discards the actions.
Hugging Face Trending Papers
Jul 7
RuBench: A Repository-Level Agentic Coding Benchmark with Natively Authored Russian Task Specifications
Developers increasingly delegate real maintenance work to product-grade coding agents, and many state tasks in their native language, in the style of a customer request rather than a curated English issue. Existing repository-level agentic benchmarks do not measure this setting: their task statements are English by design.
arXiv AI
2d ago
Not All Tokens Are Equal: Inflation-Aware Routing for Agentic LLM Systems
arXiv:2608. 13571v1 Announce Type: cross Abstract: When a language model fails to answer a query on the first attempt, an agentic system retries, consuming additional tokens each time.
arXiv AI
Jul 21
Fantastic Adaptive Taxonomies and How to Use Them
arXiv:2607. 16387v1 Announce Type: cross Abstract: An agent system's execution traces record how it fails, and procedures that improve such a system without changing model weights (trajectory selection, prompt and workflow optimization, runtime monitoring) read these traces for feedback.
arXiv Machine Learning
Aug 4
Learning Compositional Meta-Routing for Agentic Workflows: An Executable Benchmark
arXiv:2608. 00106v1 Announce Type: new Abstract: Agentic systems must decide not only what answer to produce, but which reasoning and execution operations should precede it.
arXiv AI
Jun 26
Semantic Early-Stopping for Iterative LLM Agent Loops
arXiv:2606. 27009v1 Announce Type: new Abstract: Multi-agent large language model (LLM) loops, for example a Writer that drafts and a Critic that revises, are almost always terminated by a fixed iteration cap (max_iterations).
arXiv AI
Jul 21
Retain or Consolidate? Budget-Dependent Operator Selection for Language Agent Memory
arXiv:2607. 17545v1 Announce Type: new Abstract: Language agents depend on memory across interactions.
arXiv AI
Jun 30
When LLMs Develop Languages: Symbolic Communication for Efficient Multi-Agent Reasoning
arXiv:2606. 29354v1 Announce Type: new 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 with efficient machine reasoning.
Hugging Face Trending Papers
Jul 21
RAGAL: A Frugal, Fully Local Retrieval-Augmented Assistant for Technical Support at a Government Agency
Public institutions hold large volumes of sensitive documents and support tickets that cannot leave the premises, ruling out cloud-hosted language models entirely. We report on RAGAL, a retrieval-augmented assistant for the technical-support team of AFIR, the Romanian Agency for Financing Rural Investments, built and operated under three hard constraints: zero data egress (no external API calls, even for synthetic data), a read-only mandate (the assistant drafts, humans execute), and a single 8 GB consumer laptop as the only development and training machine.
Hugging Face Trending Papers
Aug 10
Measuring the Tokenization Premium: A Cost Audit for Underserved Language Communities
Large language models are increasingly deployed as general-purpose educational and technical assistance systems, but their underlying infrastructure does not treat languages equally. One underexamined source of disparity is tokenization: semantically equivalent content can require substantially different token counts across languages, affecting API cost, latency, and usable context length before a model is invoked.