Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2607. 29468v1 Announce Type: new Abstract: Self-play agents can generate training problems without questions from target benchmarks, but their curricula lack persistent state: failures affect gradients yet do not explicitly shape future practice.
arXiv:2607. 29559v1 Announce Type: new Abstract: Reinforcement Learning (RL) systems are typically trained using a single, well-specified scalar reward function.
arXiv:2607. 28916v1 Announce Type: cross Abstract: Multistep credit assignment is critical for sample-efficient reinforcement learning, yet managing off-policy bias in Q-learning remains a fundamental challenge.
arXiv:2604. 10475v2 Announce Type: replace Abstract: Modeling household-level decisions is central to many real-world applications, including trip planning, residential mobility and migration, disaster management, etc.
arXiv:2603. 11872v3 Announce Type: replace-cross Abstract: Translating single-cell RNA sequencing (scRNA-seq) data into mechanistic biological hypotheses remains a critical bottleneck, as agentic AI systems lack direct access to transcriptomic representations while expression foundation models remain opaque to natural language.
arXiv:2605. 17877v2 Announce Type: replace Abstract: A significant hurdle for current LLMs is the execution of complex, multi-stage tasks.
Geographic Information System (GIS) professionals rely on multi-step spatial analysis workflows to support decision-making in urban planning, disaster response, and environmental monitoring. The process is tedious, time-consuming, and error-prone.
Reference-based text evaluation metrics, which are widely used to assess natural language generation systems, score a candidate response by comparing it with a reference response. The reliability of an evaluation metric is usually judged by its statistical correlation with human ratings.
We evaluate large language models (LLMs) as language agents playing goal-directed dialogue games in self-play across 30 languages: the 24 official EU languages plus six others. Unlike static or preference-based evaluation, this paradigm is multi-turn, reference-free and programmatically scored, and because the game mechanics are language-agnostic it extends to a new language by localising a fixed set of prompt and word-list files.
Two prompts can request the same code change and produce the same correct patch, yet cause a coding agent to perform radically different kinds and amounts of work. We study this effect in a preregistered benchmark spanning 4,644 valid runs, 24 deterministic coding tasks, seven reasoning models, and two real agent harnesses.
Generating long-form content from extensive internal reports remains challenging for organizations operating under strict privacy and security constraints, where proprietary cloud-based LLM APIs are often not viable. While locally deployed open-weight models offer a privacy-preserving alternative, existing retrieval-augmented generation (RAG) approaches on smaller models frequently lack effective global planning and accumulate factual inconsistencies over long outputs.
Perform non-programming tasks with coding agents The post How to Apply Coding Agents to Non-Programming Tasks appeared first on Towards Data Science .
A step-by-step guide to building, running, and monitoring a stateful customer support agent using Python, LangGraph, and Langfuse. The post I Replaced a 15-Minute Booking Process with a LangGraph AI Agent appeared first on Towards Data Science .
Tool-using language-model agents are governed not only by task prompts but also by persistent system-side instructions that specify tools, arguments, policies, execution protocols, and recovery. Compressing these agent control contexts (ACCs) can reduce input cost and context use, yet existing prompt-compression evaluations do not reveal whether the resulting control remains operationally reliable.
Large language model agents have shown strong capabilities in generating coherent and contextually appropriate responses, yet robust long-horizon dialogue remains limited by the lack of external memory that is traceable, updatable, and diagnostically transparent. Existing memory-augmented agents often store memories as isolated records or overwritable states, making it difficult to preserve how information originates, evolves, conflicts, or becomes obsolete over time.
Most coding agents treat prompt construction like retrieval: gather more files, add more context, hope the model figures it out. But that approach breaks down fast.
A hybrid LLM application pattern that combines a predefined workflow with adaptive agent behavior The post Put the Agent Inside the Workflow appeared first on Towards Data Science .
How a seemingly harmless move to a multi-agent architecture quietly tripled our LLM costs and what actually fixed it. The post The 3× Token Bill We Didn’t See Coming appeared first on Towards Data Science .
In five to ten years, the sharpest manager in your company might not be human, might not sleep, and might exist entirely in shared GPU memory. This is the systems-level view of the algorithmic corporation — why middle management collapses into a protocol, what breaks in the current AI stack, and what has to be built for autonomous agents to actually run a business.
A practical tutorial for recording model tool requests, real function results, patches, checks, screenshots, and a saved run log. The post How to Debug AI Coding Agents When They Change the Wrong Thing appeared first on Towards Data Science .