arXiv AI
DENSE: Distilling Agent Trajectories into Evidence-Grounded Shortcut Trees for Self-Refinement
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
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.
arXiv AI
Oct 21
Lost in Recovery: Demystifying Recovery Behavior of Computer-Use Agents via Goal-Oriented Action Replay
arXiv:2610.27954v1 Announce Type: new Abstract: Recent advances in large (vision) language models have enabled computer-use agents that automate digital workflows via fine-grained keyboard and mouse...
Hugging Face Trending Papers
Oct 14
TreeFlex: Agents Navigating Their Own Search Trees
A ReAct-style agent accumulates observations, intermediate results, and failed attempts in a single context. As this context grows, stale and off-path information consumes its limited capacity and obs...
arXiv AI
Oct 21
Harness Self-Evolution for Long-Horizon Terminal Agents
The paper introduces RiseHarness, a framework that iteratively refines agent harnesses while keeping model weights fixed. It uses successful and failed runs under the same configuration to analyze failures, combining agent trajectories with runtime monitor traces to understand interactions between model actions and execution components. The framework then searches other harness frameworks for relevant implementations, adapts them, and validates changes through behavioral checks and repeated task evaluation, ultimately integrating mechanisms from multiple frameworks to improve reliability across tasks.
arXiv AI
Oct 15
Long-Horizon-Terminal-Bench 2.0: Automating Diverse Task Construction and Measuring Sustained Agent Progress
arXiv:2610.14146v1 Announce Type: new Abstract: Long-horizon terminal benchmarks measure whether an agent can sustain progress through extended workflows with process rewards, not only whether its fi...
arXiv AI
Oct 15
CoEvoke: Evoking Multi-Agent Collaboration for Trajectory Collection
arXiv:2610.14021v1 Announce Type: cross Abstract: Training multi-agent collaboration requires trajectories of checking, feedback, and repair, yet task-solving rollouts may end in immediate approval o...