arXiv AI
Predict Before You Modify: Learning Improvement Dynamics for Self-Evolving Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 1
Co-Evolving Agents: Learning from Failures as Hard Negatives
The paper introduces a co‑evolving framework where a target agent improves by learning from its own failures, and a separate failure agent is trained to generate hard negative trajectories. These hard negatives, derived from plausible but incorrect attempts, help the target agent better distinguish successful behavior from subtle errors. Experiments on online shopping, scientific reasoning, and interactive SQL querying show a 5.7% average reward improvement over baseline methods.
Hugging Face Trending Papers
Aug 31
Aspire: Can Models Self-Evolve from Vague Goals?
Many important forms of human learning begin with a vague goal, such as "become a better physicist" or "improve at research." Learners must interpret the goal, identify capability gaps, decide how to...
arXiv Computation and Language
Sep 1
Aspire: Can Models Self-Evolve from Vague Goals?
The paper introduces ASPIRE, a benchmark that challenges language model agents to self‑evolve from vague, natural‑language goals without explicit evaluation metrics. In ASPIRE, agents must interpret the goal, select data and update strategies, and decide when to evaluate, all while the downstream tasks remain hidden. Experiments show that while agents can complete training loops, weight‑level improvements are sparse and unstable, and the best evolved harness still falls short of a strong engineered baseline.
arXiv AI
Jun 8
Socratic-SWE: Self-Evolving Coding Agents via Trace-Derived Agent Skills
arXiv:2606. 07412v1 Announce Type: cross Abstract: LLM-driven software engineering agents have become a central testbed for real-world language-model capability, yet their training remains limited by the availability of high-quality SWE tasks.
arXiv AI
Jun 3
SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents
arXiv:2606. 03692v1 Announce Type: new Abstract: Recent AI agents can flexibly invoke skills to solve complex tasks, but their long-term improvement is fundamentally constrained by a lack of systematic skill construction, accumulation, and transfer.
arXiv AI
Sep 4
CoMAP: Co-Evolving World Models and Agent Policies for LLM Agents
CoMAP introduces a framework that jointly evolves textual world models and agent policies through a closed‑loop interaction. At each decision step the world model forecasts future state feedback for candidate actions, while the agent reflects on the reliability of this feedback to refine its action. The resulting on‑policy trajectories are used to self‑distill and update the world model, improving prediction accuracy and long‑horizon decision‑making across embodied planning, web navigation, and tool‑use benchmarks.