Your Agent Aced the Task. Will It Do It Again?

AgentRewind: Recoverable Execution for Long-Horizon LLM Agents

arXiv:2608. 14380v1 Announce Type: new Abstract: Many real-world tasks require LLM agents to interact with their environments over long execution horizons.

AI Agents Are Here. What Now?

Computer-Using Agent

Coding Agents Can Solve the Task — But How Much Work Did They Waste?

The article "Coding Agents Can Solve the Task — But How Much Work Did They Waste?" examines the performance of coding agents using real repositories and seeded agent decisions. It reports on 50,400 runs, highlighting metrics such as wasted turns, patch churn, and the effectiveness of different harness rules. The study provides insights into how these agents manage code modifications and the efficiency of their decision-making processes.

Sentry: Learning to Recover from LLM Agent Failures at Test Time

Sentry is a failure‑management layer for large language model agents that learns from failures at test time. It retrieves relevant lessons from an external playbook when a failure occurs, verifies recovery without task rewards, and stores new lessons only if recovery succeeds, keeping the playbook out of the agent’s context. Across multiple benchmarks, Sentry outperforms both runtime‑intervention and context‑evolution baselines, and its lessons transfer to unseen tasks.

How Do Coding-Agent Harnesses Self-Evolve? An Empirical Study of Retrospective Adaptation

Coding agents can adapt their harnesses, the software, configuration, and instructions used to run them, based on experience from earlier tasks, but whether these adaptations improve their behavior on...

Agents Are Systems, Not Models: Rethinking Agentic Evaluation

The paper argues that evaluating agents as fixed models is insufficient, proposing instead to treat them as configurable systems. Using a new benchmark of four scientific tasks, the authors analyze how five configuration aspects—task information, reasoning, self‑verification, time budget, and backbone model—affect performance, noting that about 54% of outcome variance arises from run‑to‑run differences even with the same settings. The study finds that providing more task information has the strongest impact, while interactions among settings (e.g., extra time only helps with adequate information or model capability) and the choice of verification tools significantly shape agent behavior.

PAUSE: Search-Free Steering of Coding Agents Before Their First Source-Code Edit

PAUSE is a steering framework for coding agents that intervenes once before the agent’s first source‑code edit, eliminating the need for learned monitors, checkpoint searches, or extra model calls. By having a Planner generate a repair plan from the task and pre‑edit transcript, the same agent can resume execution with this plan, preserving context and workspace. Experiments on SWE‑bench Verified and Multilingual show that PAUSE improves resolution rates by up to 16.8% online and recovers 35.4% of failed tasks offline, while reducing Executor token usage by 33‑41% compared to restarts.

Agents Don't Just Agree, They Remember: Benchmarking Persistent Sycophancy in Self-Improving Personal Agents

arXiv:2607.10526v5 Announce Type: replace Abstract: Self-improving personal agents write profiles, memories, and reusable skills that carry over from one chat to the next. Prior works ask whether a m...

When to Intervene? An Empirical Study of Errors and Self-Recovery in LLM Agents

LLM agents interact with Web services to perform tasks on users' behalf. Errors during these interactions can disrupt execution and prevent task completion, motivating external intervention. However,...

Advancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems

The paper introduces AgentX-Model, a dual‑agent framework that links proposal development with model experimentation in industrial recommender systems. The Research Agent drafts proposals from literature and prior findings, while the Model Agent runs multi‑round experiments, returning code, metrics, and open questions. The framework iteratively selects starting implementations and formulates new research questions, organizing work into Reproduce, Follow‑up, Composition, and Diagnose actions. Across production evaluations, most experiments exceeded business baselines, with recent A/B tests showing significant gains in acquisition efficiency, advertising spend, and watch time while reducing computational cost.

JarvisBench: Always-on Intelligence Between Humans and Agents

arXiv:2608. 14870v1 Announce Type: new Abstract: Long-horizon agents can execute continuously, but human attention remains intermittent and scarce.