arXiv AI
Holding a Steady Course: Knowledge Evolution from Expertise and Lessons for Continual Agent Learning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
Oct 25
Holding a Steady Course: Knowledge Evolution from Expertise and Lessons for Continual Agent Learning
Autonomous agents are increasingly deployed across sequences of related tasks, yet they often fail to retain and improve their knowledge over time. Existing approaches convert interaction trajectories...
arXiv AI
Sep 23
ACLArena: Agent Continue Learning in Multi-stage Post-training
arXiv:2609.23989v1 Announce Type: new Abstract: Building general-purpose agents for industrial deployment requires integrating multiple capabilities, each typically acquired at a distinct stage of tr...
arXiv AI
Oct 16
Reliable Knowledge Acquisition for Continual Learning Agents
The paper introduces RIKA, a method for reliable knowledge acquisition in continual learning agents. RIKA hierarchically extracts factual, conceptual, procedural, and metacognitive knowledge and uses evidence-based admission to decide which claims are incorporated into the agent’s context, avoiding the reuse of unreliable information. Experiments on six task streams and four model backbones show that RIKA outperforms existing memory and experience-learning systems on aggregate performance.
arXiv AI
Oct 1
SkillMaster: Toward Autonomous Skill Mastery in LLM Agents
arXiv:2605.08693v3 Announce Type: replace Abstract: Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and...
arXiv Machine Learning
Sep 22
AhaBench: Do Agents Turn Experience into Reusable Insights? A Long-Horizon Benchmark for Continual Learning
arXiv:2609.05435v2 Announce Type: replace Abstract: Can language agents continually learn from experience, turning earlier interactions into reusable capabilities? AhaBench evaluates this ability thr...
arXiv AI
Oct 7
Learn2Play Bench: How Well Do LLM Agents Learn from Experience in Unfamiliar Environments?
Learn2Play Bench is a new benchmark that tests how well large language model agents learn from experience in unfamiliar, text‑based games with novel or counterintuitive rules. The benchmark provides reproducible feedback, automatic scoring, and varied game instances to evaluate learning across repeated attempts and transfer to new situations. Findings show that retaining full action records aids learning, human players outperform agents, and the choice of harness significantly impacts performance and inference cost.