arXiv:2608. 16211v1 Announce Type: new Abstract: Long-horizon agents are beginning to automate complete workflows that produce code, reports, and research artifacts.
arXiv:2606. 01961v1 Announce Type: new Abstract: Autonomous agents are increasingly expected to support end-to-end medical-AI research workflows, moving beyond isolated prediction tasks or short-form clinical question answering.
arXiv:2608. 07418v1 Announce Type: new Abstract: In medical education, physicians convert academic knowledge into clinical expertise through residency: years of training across thousands of encounters, with diverse sources of feedback and progressively greater autonomy.
NeoHorse-1 is a family of agent-native models that pursue recursive self‑improvement through agentic post‑training. The system uses a heterogeneous model pool with intelligent routing to record capability demands, service tiers, and interactions, converting these records into training examples that preserve reasoning, tool calls, and harness context. By structuring supervised fine‑tuning into a three‑stage curriculum and employing routing‑guided on‑policy distillation, NeoHorse-1 closes an evaluation‑selection‑update loop, raising macro‑average performance from 58.94 to 64.87 on 4B models and from 65.60 to 69.04 on 9B models across eleven benchmarks, while also producing a prefill‑only variant that outputs structured decisions and probabilities for agent workflows.
arXiv:2610.14118v1 Announce Type: new Abstract: The rapid advancement of Large Language Models (LLMs) has driven their deployment toward general-purpose harness environments, where LLM-based agents o...
arXiv:2609.13543v1 Announce Type: new Abstract: LLM agents are predominantly benchmarked on short, single-task trajectories, yet real deployments run for hours under contention, surfacing a different...
arXiv:2607. 15314v1 Announce Type: new Abstract: Healthcare spans high-stakes communication, expert reasoning, and workflow execution, yet specialized LLMs that cover these use cases together remain limited.
The paper introduces ParetoRSI-Gym, a framework for evaluating recursive self‑improvement (RSI) in language models across multiple domains—math, code, finance, medicine, and science—by having agents iteratively search for, curate, and train on data while keeping the base model, toolset, and training pipeline fixed. Experiments with three agent systems and three base models show that the best system (Claude Code with Opus‑5) improves generalization scores by an average of 9.2% relative to the starting model, with domain‑specific gains up to 63%. The study highlights that both the harness and the agent’s data‑selection strategy significantly influence outcomes, underscoring the need for realistic multi‑domain evaluation of RSI systems.
arXiv:2609.39566v1 Announce Type: new Abstract: Foundation models can serve as clinical agents through tool-use harnesses. However, conventional medical benchmarks assess reasoning over preselected e...
arXiv:2607. 23124v1 Announce Type: new Abstract: Large language model agents have advanced rapidly, yet progress remains fragmented across domains, capabilities, task difficulty, and interaction settings.
The paper introduces Self‑Direction, a method that lets agents learn from mistakes by reflecting on failed trajectories, distilling lessons into lightweight low‑rank adapters, and storing them for future use. These adapters add only about 0.02% of the base model’s parameters, keeping the original weights frozen and avoiding costly fine‑tuning. Experiments on Qwen‑based agents across research, tool‑use, and terminal tasks show 8.9–17.0 percentage‑point gains in success rates, reduced repeated errors, and transfer of lessons to new tasks.
The Agent Error Dataset (AED) presents 50,228 error–diagnosis pairs collected from 9,961 source tasks across 33 environments, 19 harness families, and 23 policy models in text‑based agent systems. A five‑stage Agentic Error‑to‑Training (AET) pipeline generates diagnoses and proposed corrections, verifies them against recorded evidence, and creates separate training views for diagnosis and actor recovery. Experiments show that first‑proposal corrections improve verifier pass rates from 18.4% to 51.1%, and fine‑tuning with full‑diagnosis data raises Qwen3‑8B’s exact‑step agreement from 47.2% to 63.6% on a holdout set.
arXiv:2607. 11175v1 Announce Type: new Abstract: The growing ability of large language models and vision language models to jointly interpret and reason over images and text is reshaping medical agents, moving them from task specific predictors toward autonomous systems that perceive, reason, plan, remember, and act in clinical environments.