arXiv Computation and Language

Local Edits, Global Ripples: Replay-Informed Policy Adaptation for Workflow Synthesis

The paper introduces RIPPLE, a method for adapting workflow-synthesizing agents through prompt-policy editing without retraining the underlying model. RIPPLE diagnoses failed execution trajectories, maps failures to specific policy segments, and restricts edits to those segments. It then evaluates candidate edits in isolation and replays only those that remain safe after composition, achieving up to a 23.1% improvement in validation success on a synthetic benchmark and positive gains on additional language‑model backbones.

arXiv AI
Sep 2

REVISE: Validity-Guided Recovery for Online Revisions in Agent Workflows

The paper introduces “Revise”, a runtime system that performs validity-guided, fine-grained recovery for online revisions in structured agent workflows. When a revision arrives, Revise intersects the change with recorded data and control dependencies, propagates the impact through the partially executed DAG, stops invalid work, preserves unaffected progress, and recomputes only the affected region. Experiments on real coding‑agent traces and LangGraph/LLMCompiler applications show that Revise matches a latest‑version oracle, reduces model calls by up to 56%, and improves service‑level objective goodput under load.

By Ruoling Qi, Xuaner Wu, Penghang Liu, Jian Chen, Yirui Liu
arXiv AI
Aug 26

When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflows

Large language model agents coordinate tasks via multi‑role, multi‑stage workflows that transform upstream state into intermediate artifacts such as summaries and plans. The study shows that when these artifacts are transformed—through compression, plan assimilation, or other handoff methods—the strict action‑binding constraints on upstream state can be weakened, turning mandatory requirements into optional information. In 1,296 synthetic episodes, direct handoff preserved all safety blockers, whereas transformed handoffs frequently deactivated or forbidden actions, but restoring full state fields or applying downstream verification can recover preservation.

By Yiheng Sun, Huifei Wang, Yancheng Zhu, Zhenyu Li, Zebin Zhao, Yifan Yuan
arXiv AI
Aug 18

AstronOS: A Unified Execution Model and Runtime for Long-Horizon Agentic Systems

arXiv:2608. 16381v1 Announce Type: new Abstract: Agentic systems often organize execution and state around a single conversation, model invocation, or agent instance, even when real work spans many calls and stages.

By Zhenhang Nie (iFLYTEK Co., Ltd., Hefei, China), Gui Zheng (iFLYTEK Co., Ltd., Hefei, China), Xudong Sun (iFLYTEK Co., Ltd., Hefei, China), Tailong Zhu (iFLYTEK Co., Ltd., Hefei, China), Bin Zhang (iFLYTEK Co., Ltd., Hefei, China)
arXiv AI
Sep 7

From Interaction Traces to Persistent Skills: Online Evolution for Computer-Use Agents

The paper introduces an online skill‑evolution framework that transforms interaction traces and evaluator feedback into a persistent, versioned library of reusable procedures for computer‑use agents. By executing each iteration against a frozen library snapshot, the system updates skills without altering the underlying model parameters. Experiments across four OSWorld domains show that the evolving library consistently outperforms an empty‑library baseline, with gains ranging from 5.7 to 18.6 percentage points, while also revealing domain‑specific temporal stability and challenges in skill retrieval and revision.

By Longtao Hu, Xiao Liang, Linchao Zhu
arXiv AI
Aug 26

TRACE: Transition-Aware Residual Control for Multi-Objective Materials Discovery

TRACE is a transition‑aware residual control framework designed to improve multi‑objective materials discovery with large language model agents. It records each local refinement as a parent‑edit‑child transition, aggregates evidence to estimate reusable edit effects, and ranks future edits by their predicted ability to reduce remaining constraint violations while protecting already satisfied objectives. In a controlled comparison, TRACE outperforms the state‑of‑the‑art LLEMA baseline, raising the macro‑average hit rate from 18.13% to 25.96%.

By Kang Zhou, Yujia Tong, Yong Tao, Jingling Yuan
arXiv AI
Sep 7

RefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Refactoring Agents

RefactorPlatform is an open‑source harness that standardizes the evaluation of repository‑scale refactoring agents by fixing the environment and systematically varying design choices such as model backbone, execution regime, and prompt specificity. Each run operates in an isolated workspace, logs detailed telemetry, and verifies changes with AST‑based checks. Experiments on 100 RefactorBench tasks show that AST‑aware chunking improves performance by 25‑30%, a lean retrieval‑augmented single agent outperforms a sub‑agent configuration, and retrieval’s accuracy gains offset its token overhead, keeping cost per successful refactoring unchanged.

By Aziz Ben Amor, Drish Mali, Mann Acharya, Vijayasri Iyer, S\'ebastien Brati\`eres
arXiv AI
Aug 20

FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis

FACET is a framework for synthesizing terminal tasks that preserves source intent and ensures cross‑artifact consistency. It reconstructs agent skills into coherent scenarios, repairs the execution environment, and uses the resulting container state as shared grounding for the instruction, solution, and verifier. By validating and repairing artifacts through execution, FACET produces complex tasks with dense executable checks and data‑efficient supervision, improving performance on Terminal‑Bench 2.1.

By Kou Shi, Zun Wang, Qisheng Su, Shiting Huang, Ziao Zhang, Zhen Fang, Qingnan Ren, Jin Liu, Yu Zeng, Yiming Zhao, Lin Chen, Zehui Chen, Feng Zhao