Introduces physical rank consistency (PRC) and ActionPiece, a learned action tokenizer that preserves local physical relationships via joint supervision of representation learning and quantization, improving autoregressive vision-language-action policy performance across multiple benchmarks.
AI Agent Papers2026
Transforms scientific code repositories into executable, agent-learnable environments that support task generation, execution, and scientific verification. Agent-guided repository transformation produces verified interaction trajectories used to train the PhAI-IDE model family. Intended for research on agent learning, scientific-code repair, and training RL/SFT models.
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.
Analyzes a failure mode in PPO critics called “Value Flattening” and proposes SP³O (Sparse PPO), which supervises a small set of well-separated states per response to mitigate flattened value estimates and improve policy learning for LLM alignment and reasoning tasks.
AI Agent Papers2026
Finds token- and API-cost-saving harness mechanisms for long-horizon coding agents using automated recursive self-improvement; packages four surviving mechanisms (action fusion, context compaction, observation archiving, delegated reading) to cut recorded token traffic ~44.7–49.0% and API cost by about one third while preserving most capability.
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.
Provides a domain-agnostic world-modeling framework that factorizes latent targets into orthogonal predictive components, with dedicated prediction branches and synthesis for multi-domain forecasting and intervention. Demonstrates improved dynamics and long-horizon rollouts across seven domains and includes experimental biological validation.
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.
Provides an open family of K–12 foundation models and a capability-oriented instruction-tuning corpus that teaches models to solve curriculum problems, map items to curriculum concepts, diagnose learner errors, and produce scaffolded pedagogical responses.
AI Agent Papers2026
Ruixun Liu, Yuxuan Wang +11School of Intelligence Science and Technology, Peking University, State Key Laboratory of General Artificial Intelligence, Peking University +2
Provides a unified benchmark and a spatially aware omni-modal model for spatial audio-visual reasoning in embodied agents — OmniEchoBench (197 scenes, 2,972 QA pairs; 900 FOA-based navigation tasks) plus OmniEcho, which adds an FOA spatial encoder to a pretrained semantic audio pathway to enable spatial QA and sound-guided navigation.
Hangyu Ran, Yuhao Zheng +3Ant Group, The Hong Kong University of Science and Technology (Guangzhou) +2
Converts natural-language SVG instructions into instance-aware six-item rubrics and uses a vision–language judge to score rendered SVGs item-by-item as dense RL rewards. Produces stronger human alignment and lifts benchmark rubric scores substantially on MMSVG datasets.