arXiv:2609.01045v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable capabilities as powerful components in agentic systems, enabling sophisticated reasoning and...
The paper introduces TerminalHorizon, an automated engine that synthesizes long‑horizon trajectories for terminal agents by reconstructing environments from real‑world professional work and progressively expanding tasks to require further exploration and improvement. Using this engine, the authors create 1.5K task environments and fine‑tune Qwen3.5‑27B, producing TerminalHorizon‑27B, which shows significant performance gains across 12 benchmarks in coding, agentic production tasks, and reasoning. Case studies demonstrate the model’s ability to experiment beyond initial solutions, refine methods based on feedback, and preserve effective improvements in final deliverables.
Recent systems for optimizing prompts, programs, and ML workflows typically rely on explicit outer-loop controllers such as evolutionary search, bandits, or textual-gradient methods. We ask a fundamentally different question: how much of this search policy can be internalized by a single tool-using agent?
arXiv:2608. 06714v1 Announce Type: new Abstract: Recent systems for optimizing prompts, programs, and ML workflows typically rely on explicit outer-loop controllers such as evolutionary search, bandits, or textual-gradient methods.
arXiv:2606. 07603v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong reasoning capabilities, yet most LLM-based agents are statically deployed and unable to improve through task interactions.
arXiv:2604. 17708v2 Announce Type: replace Abstract: Automating operations research (OR) with large language models (LLMs) remains limited by hand-crafted reasoning--execution workflows.
arXiv:2606. 26859v1 Announce Type: new Abstract: Recommendation algorithm iteration is moving from an artisanal, engineer-bound process toward an industrialized research loop, but this transition remains blocked by a structural execution bottleneck: the idea-to-launch cycle still depends on human engineers to generate hypotheses, modify production code, launch A/B experiments, and attribute online results.
Agent4RE is a self‑refining multi‑agent framework designed for end‑to‑end software requirements engineering (RE). It coordinates specialized agents and includes two iterative improvement loops, and introduces a new real‑world dataset, RE‑E2E, for evaluating RE workflows from elicitation to generation. The framework, along with two enhanced variants that use autonomous self‑refinement or structured human feedback, consistently outperforms baseline prompting methods across eight large language models, achieving higher text‑based metrics and superior human and LLM‑as‑a‑judge ratings.
arXiv:2607. 07321v1 Announce Type: new Abstract: Tool utilization enables Large Language Model (LLM) agents to interact with the real world and resolve complex tasks.
The paper introduces KNOWS, a benchmark for evaluating web agents that act as assistants by retrieving, synthesizing, and presenting information across complex, multi-step browser tasks. It outlines a task design rubric, evaluation protocol combining deterministic checks with LLM judgments, and reports that current agents achieve only modest success, with the best performing agent succeeding on less than 3% of tasks. The study highlights significant gaps in agents’ tool use, visual understanding, and long‑horizon reasoning.
arXiv:2608. 02650v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly rely on external tools to complete complex real-world tasks.
Large Language Models (LLMs) have driven rapid progress in autonomous agents, yet standard evaluations remain confined to static task solving. An emerging frontier is harness evolution---the agent's capacity to autonomously optimize its own operating harness.