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...
The paper introduces StepLearn, a nonparametric framework for prequential test‑time learning in large language model agents. StepLearn separates immediate use of informative transitions from persistent trust, turning each transition into a hypothesis that guides the next step and only reusing it after prospective validation across episodes. Experiments on WebArena‑Lite and ALFWorld show StepLearn improves success rates by 2.2–12.7 percentage points over the strongest baseline, with benefits evident from the first task attempts.
arXiv:2608. 03206v1 Announce Type: cross Abstract: Large language models (LLMs) power educational applications from tutoring to essay scoring, but each is a point solution to a single task, and only recently have these point solutions been integrated into agents operating over a learning management system (LMS).
LLM agents are increasingly evaluated on multi-week decision tasks in which the state that drives cost is never directly observed. On such tasks the final cost cannot say why an agent failed: it may have misread the world, or read it correctly and still failed to act (the knowing-doing gap).
arXiv:2607. 13618v1 Announce Type: new Abstract: LLM agents are increasingly evaluated on multi-week decision tasks in which the state that drives cost is never directly observed.
arXiv:2605. 17554v2 Announce Type: replace Abstract: Frontier deep research agents (DRAs) plan a research task, synthesize across documents, and return a structured deliverable on demand.
The study demonstrates that governance records—structured logs linking task contracts, model attempts, verifier decisions, and outputs—can serve as effective supervision for bounded AI models. Using a verifier-selected self‑training approach, the authors show that a Qwen3‑14B model trained on plans accepted by an independent VAL verifier achieved significant gains in plan acceptance across numerous PlanBench replanning cases, outperforming other selection strategies. The results highlight the feasibility of one‑shot execution and cumulative learning without relying on oracle targets or stronger teachers.
The paper introduces ACES (Agentic Continuous Evaluation of Skills), a framework that evaluates reusable skills and capability packages by running paired live trials with and without a target skill, normalizing results into the Agent Trajectory Interchange Format (ATIF), and grading six runtime metrics to compute Skill Lift. ACES demonstrates that scan-only gates miss important aspects of skill performance, while the evaluation protocol reveals significant improvements in skill execution, behavior check, and skill efficiency across 145 real skills and 947 scored cases. The open‑source NVIDIA SkillEvaluator implementation enables reproducible, repository‑native assessment of agentic skills in production environments.
APEX-EM is a non‑parametric experience memory that stores full procedural‑episodic traces in a typed Procedural Knowledge Graph and retrieves them via semantic search, structural‑signature matching, and graph traversal. It uses a Plan‑Retrieve‑Generate‑Iterate‑Ingest workflow to produce, quality‑gate, and commit experiences, indexing both successes and failures so the agent learns what to reuse and what to avoid. Evaluations on five benchmarks with a shared GPT‑4o backbone show significant performance gains, such as +7.6 pp on BigCodeBench transfer and +1.4 pp on Lifelong Agent Bench, demonstrating that the memory adds to model capability rather than replacing it.
arXiv:2607. 23124v1 Announce Type: new Abstract: Large language model agents have advanced rapidly, yet progress remains fragmented across domains, capabilities, task difficulty, and interaction settings.
arXiv:2607. 17044v1 Announce Type: cross Abstract: Multi-step enterprise agent tasks fail in a characteristic way: single-pass inference has no checkpoint between deciding an answer and committing to it.
arXiv:2609.00892v1 Announce Type: new Abstract: Rubric-based reinforcement learning decomposes open-ended instructions into prompt-specific, flexible rubrics, making it better suited than reinforceme...