AI Agent Papers2026
Evaluates whether coding agents can modify real scientific software while preserving domain-specific scientific contracts. Contains 119 repository-level tasks across 98 GitHub projects and 20 scientific domains, measures reproducible edits in pinned Docker images, and analyzes recurring failure modes.
AI Agent Papers2026
Defines recursive self-improvement (RSI) with an evaluation metric (Headroom-Closed Index) and a five-level autonomy roadmap—from executing human-specified improvements to recursively improving improvement mechanisms—while analyzing scenarios, verification challenges, and governance risks.
AI Agent Papers2026
Extracts replayable behaviors from working web apps and converts them into verifiable, reference-guided software-engineering tasks to evaluate and diagnose coding agents; includes an automated pipeline that scales to thousands of tasks.
AI Agent Papers2026
Measures how individual harness components—planning, action space, and context management—affect coding agents' success, cost, and behavior. Uses a modular harness across 176 matched settings on SWE-Bench Verified and Terminal-Bench 2.1 to isolate component effects and surface model- and budget-dependent trade-offs.
AI Agent Papers2026
Provides reproducible, multi‑platform environments and execution‑grounded verification for hybrid computer‑use agents that interleave GUI exploration and code/CLI. Key features: a five‑platform harness, RecreationBench (250 tasks), reference‑grounded programmatic and visual assertions for automatic scoring.
Turns implemented functionality in open-source codebases into executable RL training environments by automatically generating behavioral specifications, execution-grounded tests, and post-rollout filtering; yields 5,545 verifiable coding tasks across 23 languages to train coding agents.
AI Agent Papers2026
Shuang Sun, Guoxin Chen +7Affiliation: Gaoling School of Artificial Intelligence, Renmin University of China
Edits an LLM agent's internal task state and action continuations to remove unsupported assumptions and noisy plans, improving downstream decisions instead of reconstructing high-entropy tool outputs. Combines Action Judge, State Revision, and EditAct and shows consistent gains across benchmarks and agent backbones.
AI Dataset2026
Provides mixed-domain, verifiable RL training environments for LLM agents (code, cyber, knowledge work, web dev, music) as Parquet datasets, with domain-specific verifiers, Docker artifacts and links to training code for reproducible agentic RL experiments.
AI Model2026
Text-only sparse Mixture-of-Experts language model for long-context reasoning, coding, and agentic tool use; 501B total / ~23B active parameters, 1M-token context, and BF16/FP8/NVFP4 checkpoints released under Apache 2.0.
AI Agent Papers2026
Jiahao Wang, Hongjin Qian +3Beijing Academy of Artificial Intelligence, Institute of Automation, Chinese Academy of Sciences +1
Measures whether coding agents can build agents that truly satisfy natural-language requirements via AgentSWE: a 25-task benchmark spanning Creation, Editing, and Optimization. Builders develop against few illustrative cases; acceptance runs frozen submissions on held-out cases and requirement-derived rubrics, exposing overfitting, hollow runtimes, and unsupported completion claims.
AI Agent Papers2026
Alternates harness and policy optimization so a coding agent uses its own policy to propose harness revisions that target evolving failure modes. Combines harness search (H-step) with RL-based policy updates (P-step), improving resolve rates on multiple coding benchmarks and generalizing out-of-distribution.
AI Model2026
Helps coding agents investigate codebases, fix bugs, implement features, and write tests. Its mixture-of-experts design activates about 2.5 billion parameters per token and supports reasoning and multi-turn tool use.