arXiv AI
Beyond Outcome Feedback: Trajectory-Quality-Guided Experience-based Learning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Sep 1
Retrieval-Augmented LLM Agents: Learning to Learn from Experience
arXiv:2603.18272v2 Announce Type: replace Abstract: While large language models (LLMs) have advanced the development of general-purpose agents, robust generalization to unseen tasks remains challengi...
arXiv AI
Oct 16
MetaExp: Learning to Self-Improve through Experience via Verifiable Cross-Task Environment Scaling
MetaExp is a framework that trains language‑model agents to learn reusable experience across tasks by using verifiable cross‑task environment scaling. It introduces two designs—Shared‑Tool families that keep black‑box tools constant and Shared‑Workflow families that preserve latent procedures—allowing agents to acquire operational and procedural experience respectively. After fine‑tuning Qwen3.5‑122B‑A10B on thousands of trajectories from 1,000 task families, MetaExp achieves significant performance gains on benchmarks such as SpreadsheetBench, APEX‑Agents, and AutomationBench, with improvements persisting even when domain‑excluded training is applied.
arXiv AI
Sep 15
CLEAR: Context Augmentation from Contrastive Learning of Experience via Agentic Reflection
arXiv:2604.07487v2 Announce Type: replace Abstract: Large language model agents rely on effective model context to obtain task-relevant information for decision-making. Many existing context engineer...
arXiv AI
Aug 18
Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents
arXiv:2608. 15071v1 Announce Type: new Abstract: Learning from experience is critical for developing capable, self-improving large language model (LLM) agents.
arXiv Machine Learning
Oct 8
ExperienceIndex: Artifact-Grounded Memory
arXiv:2610.10091v1 Announce Type: cross Abstract: Knowledge-intensive tasks require answering many questions by reasoning about a shared corpus of artifacts (e.g., court cases, or scientific literatu...
Hugging Face Trending Papers
Aug 3
CRISP: Critical Step Perception for Training Efficient Deep Search Agents
Large language models (LLMs) are increasingly extended into deep search agents that solve complex questions through multi-step interaction with external search and browsing tools. However, existing agents often incur substantial computational and interaction costs, generating lengthy trajectories that contain redundant queries, inefficient exploration, and irrelevant observations.