The paper introduces Hindsight Structured Advice Distillation (HSAD), a method that trains a small advisor model to generate structured guidance for a frozen executor language‑model agent. By analyzing executor failures on a training set, a teacher writes advice that would have helped, and the advisor learns to produce this advice from input alone, adding minimal latency. Experiments on the FrontierFinance benchmark show that an 8B advisor boosts the qualification rate of Samaya’s research agent from 52.9% to 56.6%, surpassing the agent’s high‑effort configuration while cutting cost per query by 37%, and the approach also improves performance on WebShop, BIRD text‑to‑SQL, and ExpertLongBench.
arXiv:2510.13935v3 Announce Type: replace-cross Abstract: The facts a language model stores are tied to its parameter count, so small models that fit on edge devices fail on expert problems, which ne...
AdaTutoRank introduces a setwise document reranker that uses Adaptive Tutoring Optimization (ATO) to provide graded supervision across nine rubric dimensions. By generating hint‑based silver labels, reinforcement rewards, and distillation cues tailored to each rollout’s quality, the method improves credit assignment for individual documents within a set. Experiments on ten benchmarks covering Retrieval‑Augmented Generation (RAG), deep research, and setwise evaluation show that AdaTutoRank achieves superior overall performance while reducing the number of retrieval calls.
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.
arXiv:2609.38142v1 Announce Type: new Abstract: A small trainable advisor can steer a frozen language-model executor using natural-language advice. In addition to learning from task rewards, the advi...
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...
FinSkillBench is an evaluation suite that tests whether language model agents can use financial domain skills to solve investment management tasks across portfolio construction, risk management, and fundamental analysis. The benchmark contains 12 subtasks with 2,603 episodes, each providing point‑in‑time inputs, hidden ground truth, and a verifier. Experiments show that curated skill packages improve performance significantly, while self‑generated skills offer little benefit, indicating that reliable procedural skills are crucial for effective AI agents in this domain.
The paper introduces Recursive Reward Improvement (RRI), a method that enhances recursive self‑improvement loops by using an adversary to expose and fix weaknesses in model‑generated rubrics for open‑ended tasks. In RRI, an adversary crafts a rubric‑gaming answer, an honest answer is generated without rubric exposure, and up to two repair steps adjust the rubric so the honest answer scores higher. Experiments on HealthBench Professional show that RRI boosts adjusted scores by up to 12.4 points on a 27B model and yields significant gains on difficult and writing tasks, while also improving performance on unseen benchmarks PRBench Hard and ProfBench.
Navalia is a framework that advances cowork agents by combining verifiable task synthesis with long‑horizon post‑training. It selects supporting evidence from corporate financial reports, builds executable computation chains, and uses independent LLM review and programmatic checks to ensure evidence consistency and answer correctness. The verified tasks are then used for trajectory collection, supervised fine‑tuning, and reinforcement learning, yielding consistent performance gains over the base model across five financial and office‑task benchmarks.
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).
SkillLift introduces a method for efficiently evolving reusable procedural prompts (skills) in large language model agents by learning a dense rubric that aligns with sparse oracle evaluations. Instead of directly revising skill text based on costly full agent rollouts, the approach decouples skill search from oracle cost through a bilevel optimization framework: an inner loop uses a frozen rubric as a cheap surrogate to guide skill updates, while an outer loop periodically realigns the rubric using a small number of oracle rollouts via rank correlation. Experiments on complex agent task benchmarks demonstrate that SkillLift outperforms existing auto-skill methods while reducing token cost by 40–70% compared to frontier-evolving approaches.
arXiv:2610.09430v1 Announce Type: new Abstract: Internalizing external skills changes a language agent's capabilities and, with them, the value of its remaining guidance: rules can become redundant,...
PRISM is a training‑free framework for financial information retrieval that combines prompt engineering, in‑context learning, and a candidate refinement module, with optional multi‑agent coordination. On FiQA‑2018 it improves Recall@100 from 0.7783 to 0.8326, and on FinAgentBench it achieves a Cohere‑refined top‑50 pool that raises NDCG@5 while cutting per‑query cost by about 35%. The authors also release an expert‑annotated evaluation set, a label‑robustness sweep, and a Pareto frontier of quality‑cost‑latency trade‑offs, and PRISM ranks third on the private FinAgentBench leaderboard without fine‑tuning.