The paper proposes that self‑evolving large‑language‑model agents can only be safely reviewed if their changes are confined to the runtime harness—instruction text, tool‑call logic, and primitive composition—while the model weights remain fixed. A dual‑loop engine with an admission gate records a hash‑chained diff before deployment, and simulation experiments show that this gate admits only safe changes, preventing error increases and maintaining false‑positive rates. When the gate is removed, many harmful changes slip through and missed flags rise, illustrating the gate’s protective role.
By Ravil Akhtyamov
The paper introduces a self‑healing harness that enforces admission control over language‑model agents’ self‑modifications. The harness runs a Detect‑Notice‑Heal‑Validate loop, allowing agents to propose rule changes that are only granted persistent authority after demonstrating improvement on a failure case without regressing on protected cases. Across 16 benchmark runs, the harness rejected many locally beneficial proposals that caused collateral regressions, while improving task‑completion scores and reliability.
By Sina Tayebati, Divake Kumar, Nastaran Darabi, Ranganath Krishnan, Amit Ranjan Trivedi
The paper argues that using a large language model (LLM) as the sole judge in self‑improving agent pipelines is problematic, as the judge can be biased or manipulated, leading to false confidence in system performance. The authors propose a new framework, PROCTOR, which replaces the oracle judge with a deterministic, teacher‑student loop that enforces guardrails such as sandboxing, role separation, and acceptance checks to prevent cheating and ensure reliable evaluation. Experiments across contract analysis, compliance review, and code quality demonstrate that PROCTOR mitigates eleven identified failure modes that previously allowed agents to achieve perfect scores while hiding significant capability gaps.
By Vansh Wahi
arXiv:2608. 16852v1 Announce Type: new Abstract: Regulatory compliance monitoring in deployed language models is increasingly implemented as a legal and audit control, checking model outputs against written rules spanning data protection, healthcare, financial regulation, and platform policy.
By Saisab Sadhu, Aadit Sengupta, Vinay Kumar Sankarapu, Pratinav Seth
arXiv:2607. 16345v1 Announce Type: cross Abstract: Modern agentic systems increasingly rely on skills: installable packages of natural language and code that teach an LLM agent to perform a domain task.
By Tejas Singh Anand, Yuet Ying Christina Wang, Wanting Jiang, Steve Masson, Tian Zheng, Bingjie Zhou
arXiv:2607. 08124v1 Announce Type: cross Abstract: The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies intermediate results, and recovers from failures.
By Jun Nie, Yonggang Zhang, Jun Song, Qianshu Cai, Dahai Yu, Yike Guo, Xinmei Tian, Bo Han
arXiv:2606. 10241v1 Announce Type: new Abstract: Autonomous improvement loops are hard to trust because the improvement process is usually external scaffolding bolted onto the agent: failures go unlogged, diagnoses cannot be replayed, and promote-or-discard decisions land in a side database rather than the agent's own history.
By Yohei Nakajima
The paper introduces a method for co-evolving inspectable verifiers alongside self-improving agents. By synthesizing verifiers from clustered failures and selecting them based on agreement with a reference set, the authors demonstrate improved held‑out agreement on MBPP+ and outperform a bare LLM judge. They also show that removing anchor guards collapses the verifier into a vacuous grader, yet the collapsed verifier still trains skills effectively, indicating that downstream task scores cannot certify a self‑evolved verifier.
By Xing Zhang, Guanghui Wang, Yanwei Cui, Ziyuan Li, Wei Qiu, Bing Zhu, Peiyang He
The paper introduces VERSE, a Verified Self‑Evolving optimizer that enhances LLM agent harnesses by allowing the optimizer to test edits, replay failures, and perturb steps while tracking fixes and regressions. VERSE builds its own tools for failure analysis, verification, training audits, and workflow control, and uses this feedback to revise the harness’s prompts, skills, tools, hooks, and notes without changing model weights. In experiments across five executors and multiple languages, VERSE improves all evaluated harness optimizers, achieving higher accuracy on held‑out and out‑of‑distribution tasks compared to the strongest baselines.
By Zekai Wang, Yingqiang Ge, Zekun Wang, Hai Wang, Yuhui Xu, Joshua Frandsen, Shancong Fu, Ashia C. Wilson, Chandan K. Reddy
arXiv:2607. 12790v1 Announce Type: new Abstract: Self-evolving agent systems improve by creating, revising, and retiring their own skills, but every such loop rests on a hidden assumption: a reliable evaluation metric already exists.
By Xing Zhang, Guanghui Wang, Yanwei Cui, Ziyuan Li, Wei Qiu, Bing Zhu, Peiyang He
The paper introduces the Alignment Flywheel, a governance‑centric hybrid multi‑agent system (MAS) that separates decision generation from safety governance. It defines a Proposer that generates candidate trajectories, a Safety Oracle stack that evaluates safety, and an Enforcement layer that applies risk policies at runtime. A governance MAS oversees monitoring, red‑teaming, verification, and versioned release management, enabling patch‑local fixes to safety failures without retraining the Proposer. The architecture is implementation‑agnostic and is demonstrated in two scenarios: a learned spatial Oracle and a clinical GenAI proxy. The authors provide open‑source code at https://github.com/decide-ugent/Alignment-Flywheel.
By Elias Malomgr\'e, Pieter Simoens
The paper introduces TRACE, a protocol designed to diagnose whether changes in verifier scores for large language model agents reflect actual changes in agent behavior or merely alterations in the evaluation process. TRACE works by applying targeted changes to evaluation components, running paired experiments, and re‑scoring unchanged trajectories to isolate the source of score variation. Experiments on synthetic tasks and public benchmark tasks demonstrate that seemingly significant score shifts can often be attributed to evaluation artifacts, while TRACE can also detect genuine behavioral changes.
By Radhika Gaonkar