AI Dataset2026
Turns chemistry and molecular-property questions into verifiable short-answer tasks for language-model training and evaluation, with nearly 50,000 questions drawn from multiple datasets.
AI Agent Papers2026
Jianlyu Chen, Yuyang Hu +9Beijing Academy of Artificial Intelligence, University of Science and Technology of China +2
Distills operational know‑how from ML GitHub repositories into compact, verified 'skills' that research agents can load and reuse. Produces a skill format (SKILL.md, references, scripts), the AREX‑Skill Library (5,000+ skills from 1,000 repos), and demonstrates sizable benchmark gains when agents use skills.
AI Agent Papers2026
Yuling Shi, Zhensu Sun +4Shanghai Jiao Tong University, Shanghai, China, Singapore Management University, Singapore +2
Predicts an LLM agent's final success or failure from partial execution traces and halts runs when outcomes are confident to save per-task compute. Uses LightGBM success/failure classifiers on behavioral, textual, and reference features; cuts 13–26% steps and up to 44% input tokens on benchmarks.
Selectively admits dense token-level teacher supervision only after a prompt-level verifier audit, routing prompts that fail the audit to verifier-grounded trajectory supervision instead — reducing harmful updates from confidently wrong teachers and improving teacher GPU utilization.
Teaches how to build and evaluate AI agents, from hand-written RAG and tool loops to memory, optimization, and safety. Two applied assignments and a quarter-long project connect design decisions to measured reliability.
AI Agent Papers2026
Presents two LLM-based search agents (Iris-mini and Iris-pro) trained by alternating supervised fine-tuning and reinforcement learning against live web search. Key features: web-graph-derived multi-hop tasks with entity abstraction, SFT–RL climbing, inference-time context management, and state-of-the-art open-source benchmark results.
Converts a natural-language function specification into a reusable local neural function by using teacher models to synthesize examples and finetuning a small adapter for a compact interpreter. Achieves higher semantic accuracy (83.6% on FuzzyBench-Hard) at the cost of roughly one minute compile time; produces versionable PAW artifacts for local deployment.
Combines sparse verifier outcomes with dense privileged‑hindsight token scoring to learn an outcome‑calibrated, normalized distribution over complete responses for on‑policy self‑improvement. Key features: sign‑gated guidance (retain/reverse/disable per verifier advantage), profiled trajectory balance with one log‑partition per rollout group, and explicit correction against false‑positive self‑guidance.
AI Agent Papers2026
Sihan Ge, Yichen Lin +4Affiliation: Cardinal Operations, Affiliation: Shanghai Jiao Tong University, Shanghai, China
[email protected] {linyichen, chenyuzhou, linjianghao, taoyao, ddge}@sjtu.edu.cn
* Equal contribution † Corresponding authors
Studies when and how an assistant should ask clarification questions before converting natural-language problem descriptions into optimization models. Introduces OR-Clarify, a benchmark for pre-formulation clarification, and InterOPT, a two-stage framework that diagnoses formulation-critical gaps and guides targeted questioning and stopping decisions.
Provides a diagnostic benchmark of 4,084 multiple-choice questions derived from longitudinal wearable time series, blood biomarkers, and demographics of 200 users to evaluate LLM reasoning on real-world wearable data. Uses 16 question types across complementary axes and a dual-grounding framework combining literature findings with population statistics.
AI Agent Papers2026
Transforms source code into verifiable, reusable agent skills by extracting atomic operations, workflows, and recurring patterns and validating them via source-body-blind reconstruction. Produces CodeSkillBank (1,006,822 accepted records from 19,769 GitHub repos) and yields ~11.7% average downstream improvement.
Trains a world-action model that predicts future visual states to guide zero-shot robotic manipulation; introduces CoAE, SVP, IDM and KASO to pretrain generative and action components from scratch on manipulation data, scaling up to 30,000 hours and improving zero-shot success.