LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it improves. While recent environment generation methods attempt to address this, they require domain-specific pipelines, rely on expensive or unreliable verifiers, and still produce static environments.
arXiv:2608. 19880v1 Announce Type: new Abstract: LLM agents learn by interacting with environments, yet these environments are hand-built and static: blind to an agent's weaknesses, and quickly left behind as it improves.
arXiv:2609.05576v1 Announce Type: new Abstract: The paradigm of LLMs has rapidly shifted from passive language interfaces to autonomous Claw-like agents that execute long-horizon tasks across statefu...
arXiv:2607. 01084v1 Announce Type: new Abstract: While Large Language Model (LLM) agents demonstrate proficiency in static benchmarks, their deployment in real-world scenarios is hindered by the dynamic nature of user queries, tool sets, and interaction dynamics.
SPADE (Self-Play in Adaptive Synthetic Executable Environments) is a reinforcement‑learning framework where a single large language model acts as both an Environment Designer—creating executable, long‑horizon training environments—and a Reasoning Agent—learning to act within those environments. The framework uses a regret signal based on the difference between rewarded performance with and without privileged hints to guide the Designer toward environments that are challenging yet solvable. Experiments show that, when scaled to 30‑billion‑parameter models, SPADE outperforms fixed‑environment baselines by significant margins across math, science, code, and reasoning benchmarks, and improves tool‑use performance on BFCL‑v4 and ACEBench‑Agent. whyItMatters":"By making environment design a learnable component, SPADE enables continuous self‑improvement and demonstrates that adaptive, self‑generated training environments can substantially boost language‑model performance across diverse tasks."
arXiv:2607. 13705v1 Announce Type: new Abstract: As Large Language Models (LLMs) evolve into autonomous agents, the need for unified evaluation infrastructure becomes critical.
The paper introduces Env‑Rethink, a 27B post‑trained model system designed to help large language model agents better interact with complex, evolving environments. It builds Collection Maps and Event Logs to organize scattered information, uses offline trajectory learning to detect noise, and generates virtual event histories to evolve environments for more challenging tasks. Experiments show that Env‑Rethink improves downstream task performance by over 15.1% rubric pass rate across nine models on 30 tasks.
arXiv:2605. 27898v2 Announce Type: replace Abstract: As LLMs are increasingly deployed as agents, reliable assessment of their agentic capabilities has become essential.
As Large Language Models (LLMs) evolve into autonomous agents, the need for unified evaluation infrastructure becomes critical. However, current evaluation pipelines remain highly fragmented and tightly coupled, hindering reproducibility and causing redundant engineering.
arXiv:2607. 14159v1 Announce Type: new Abstract: An agent harness is the external control layer that turns a base LLM into an executable agent by managing context, tools, orchestration, memory, decoding, and output handling.
arXiv:2608.21898v1 Announce Type: new Abstract: Web agents promise to automate complex digital workflows, but their training remains limited by synthetic environments that look plausible while hiding...
arXiv:2608. 04934v1 Announce Type: cross Abstract: Training LLM agents commonly relies on supervised fine-tuning from expert trajectories or online reinforcement learning over human-specified tasks with handcrafted verifiers.
The paper introduces "environment evolution," a method that incrementally raises the difficulty of interactive environments off‑policy, scheduling their generation across training generations to supply continuous learning signals. It derives three evolution directions tied to a multi‑turn learning objective and implements them via a loop‑engineered multi‑agent harness. Experiments with models such as Hy4 preview, Claude Opus 5, GPT‑5.6 Sol, Qwen3.6‑27B, and Qwen3.6‑35B‑A3B demonstrate that this approach consistently creates harder environments and boosts terminal‑agent performance on Terminal‑Bench 2.1 by 14.4–18.0 percentage points.