The paper introduces TEAL, an unsupervised framework that allows coding agents to automatically build and refine reusable tools for data‑lake analytics without requiring labeled questions. TEAL employs an Explorer that proposes tools from the data lake and a Critic that evaluates proposals based on the agent’s own execution traces, retaining only changes that the agent adopts without extra steps. Experiments on KramaBench and LakeQA show that TEAL consistently improves performance across multiple LLM workers, especially under tight step budgets, and that synthetic question generation (TEAL‑Q) can match real‑question evolution.
arXiv:2605. 28556v2 Announce Type: replace Abstract: As agent capabilities advance, existing benchmarks, such as $\tau^2$-Bench, are becoming increasingly saturated.
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.
Self-evolving agents can continually improve their behavior, while tools define the executable action space through which they interact with the environment. However, exposing the full tool library to...
Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows. Existing MCP environment-scaling methods are data-centric: they firs...
Terminal-Universe is a framework that converts large collections of terminal-based agent trajectories into reusable, executable environments. By replaying recorded file operations and filling missing files with a completion agent, it reconstructs the original workspace and generates new tasks, scaling them in breadth (cross-workspace queries) and depth (multi-round interactions). The resulting 37.3k task-sufficient environments enable significant performance gains when fine‑tuning language models on terminal‑centric benchmarks.
Agent‑R$^2$ is a real‑source data synthesis framework designed to scale training data for realistic productivity work. It generates task instances by grounding synthesis in real occupational seeds, corpus‑derived workflow evidence, and authentic web‑sourced files, producing 4,000 task instances with fine‑grained, deliverable‑level rubrics. A 4B‑parameter model trained on this data outperforms larger baselines on GDPval and OfficeQA, while reducing shortcut behavior and encouraging sustained exploration.
Data World proposes a multi‑agent engine that generates synthetic data environments, tasks, and evaluation rubrics by first specifying the underlying world rather than curating real files. The system produces thousands of training tasks across diverse domains and enables independent audits of target recoverability, while human curation ensures realistic question selection. Benchmark results show that models trained on these synthesized tasks still face significant challenges, yet RL‑zero training on the synthetic data yields measurable performance gains over baseline models.
arXiv:2512. 13278v2 Announce Type: replace-cross Abstract: Agentic reinforcement learning has advanced large language models (LLMs) to reason through long chain-of-thought trajectories while interleaving external tool use.
arXiv:2606. 12674v1 Announce Type: new Abstract: Compact language models (LMs) reduce cost, latency, and deployment risk for tool agents.
arXiv:2610.24899v2 Announce Type: replace-cross Abstract: While LLM agents are increasingly capable of gathering and synthesizing evidence from a single homogeneous source, such as structured tables...
arXiv:2511. 20297v2 Announce Type: replace Abstract: Large Language Model (LLM)-based agents are increasingly capable of complex, multi-step tasks such as GUI automation, tool use, and data manipulation, yet they cannot learn from experience: each new session rediscovers solutions from scratch.
The paper introduces a self‑evolving harness framework where a frozen language‑model agent first solves tasks and then edits its own harness based on run records. Using a 49‑line seed harness, the evolved harness improves average scores on in‑distribution benchmarks by 4.48 points and on out‑of‑distribution benchmarks by 12.64 points, surpassing Codex on the former and matching it on the latter. Continued evolution on a specific out‑of‑distribution benchmark further raises performance, and the study analyzes emergent mechanisms such as output truncation and history compaction.