EvoUndo is a framework that enables large language model agents to self‑evolve—modifying prompts, tools, and execution harnesses—while ensuring that these changes can be reliably reversed across different states. The study evaluates EvoUndo on 600 unseen one‑shot self‑evolution tasks, finding that 197 capability‑improving mutations fail recoverability checks. By extending the recovery language and adding exact state‑address diagnostics, the framework recovers up to 191 out of 197 failures, demonstrating that robust self‑evolution requires co‑designing verification, grounding, witness semantics, and recovery expressivity.
arXiv:2610.22984v1 Announce Type: new Abstract: Experience-driven self-evolution offers a promising path for large language model (LLM) agents to continually improve through interaction. Yet existing...
arXiv:2607. 26598v1 Announce Type: cross Abstract: Large language model (LLM) agents may recover from a failure within an episode or after a retry, yet the same execution failure can recur in later tasks because post-episode feedback rarely revises the persistent harness that guides future interactions.
LegoEnv introduces a new paradigm for creating agentic environments by recombining reusable atoms—intent, rule, data, and server—rather than building each environment from scratch. The system automatically evolves these atoms when an environment fails to provide reliable feedback, leading to a significant increase in solvable environments from 71.6% to 88.3% after one evolution round. Experiments on AutomationBench show that training on LegoEnv environments doubles the performance of large language models, with SFT boosting Qwen3.6-27B from 16.0% to 32.0% and RL improving Qwen3.8-27B from 37.6% to 40.3%. whyItMatters":"LegoEnv’s modular, self‑evolving approach enables scalable, generalizable environment construction that directly enhances the training and performance of LLM agents on diverse tasks."
VeriEvolve is an evaluator-first evolution framework that first builds an executable evaluator from task instructions, then uses this evaluator as a frozen fitness signal while evolving agents. The system generates challenge states and counterfactual test cases to refine the evaluator across rounds, producing 30 evaluators for 30 MCPMark Filesystem tasks with perfect agreement on generated suites and high agreement on held-out states. Evaluator-guided evolution significantly improves externally verified success rates for GLM-5.2 and Claude, and cross-environment studies reveal complementary limits from observability, state representation, and search/execution capacity.
arXiv:2610.17609v1 Announce Type: new Abstract: Training-free self-improvement lets an agent use feedback to revise the response it is about to return and to update the harness state that shapes how...
arXiv:2608. 07545v1 Announce Type: cross Abstract: An LLM agent's capability depends not only on model weights but on its harness: prompts, tools, skills, and control flow.
arXiv:2606. 01416v1 Announce Type: new Abstract: Tool-augmented large language model (LLM) agents rely on orchestration layers that coordinate planning, retrieval, tool invocation, validation, memory, and recovery.
arXiv:2607. 17352v1 Announce Type: new Abstract: Designing effective Lean proof agents is a central challenge in formal mathematical reasoning.
The paper introduces a domain‑specific debugging agent for repairing near‑miss accelerator kernels, arguing that debugging is more efficient than regenerating kernels from scratch. It tackles knowledge scarcity, integrity, and cost control through pattern retrieval, anti‑cheat detection, and convergence safeguards. Empirical results show the debug agent achieves a 66.7% Pass@1 rate and uses 92.8% fewer tokens per success compared to traditional regeneration methods.
arXiv:2608. 02712v1 Announce Type: cross Abstract: Kernel generation for hardware accelerators such as GPUs and NPUs has become a proving ground for large language models (LLMs), and state-of-the-art systems raise correctness through pipelines that couple LLMs with agentic reinforcement learning and evolutionary search.
arXiv:2609. 04875v1 Announce Type: cross Abstract: Long-running LLM agents are stateful: beyond the transcript they accrete compressed summaries, plaintext memory, pending tool plans, and, under every serving API, a KV cache.
arXiv:2606. 17546v1 Announce Type: new Abstract: Self-evolving LLM-based agents improve mainly by changing their agent harness: the structured execution layer around a base model, including prompts, memory, tools, middleware, runtime state, and the model-tool interaction loop.