AI Agent Papers2026
Introduces an open-source multi-agent harness that automatically constructs, composes, and evolves modular model–harness units for long‑horizon, cross‑domain workflows. Key ingredients include a Host Agent for task decomposition and orchestration, EverOS for durable memory, and a Skill Forge of reusable procedures to improve task coverage via composition.
Improves test-time scaling of looped transformers by adaptively assigning extra recurrent iterations to tokens that benefit most. TaH2 is a post-training method that jointly trains an iteration decider with the backbone using lookahead depth supervision, boosting the accuracy–compute slope and peak accuracy on challenging benchmarks.
Compresses recurrent states in linear-attention LLMs via spatial–temporal post-training quantization, allocating bits by error lifetime and per-row impact to preserve accuracy (6-bit ≈ FP32) while cutting serving memory up to 68.7%.
Tong Zheng, Skylar Zhai +8University of Chinese Academy of Sciences, University of Minnesota Twin Cities +6
Calibrates multi-reward reinforcement learning by adaptively upweighting infrequently active rewards per rollout batch, so sparse objectives provide stronger signals when they matter. Proposes an inverse-square-root density correction and shows faster learning on tool-calling and math-reasoning tasks.
AI Agent Papers2026
Runs an open-source personal software agent across a user's devices to perform actions, keep readable provenance-backed memories, and coordinate via a self-hostable relay. Ships minimal end-to-end clients (mobile, desktop, web) under GPL-3.0; model-agnostic and designed for inspectability and device
Serves token-level routed LLM inference by dispatching requests to per-model asynchronous subservers and using delayed-batching scheduling to reduce admission latency and step desynchronization. Exposes a request-centric route-send-receive API and reports 2.01–64.15× decoding throughput gains versus single-LLM servers.
AI Agent Papers2026
Chengyi Yang, Renxu Bao +11Affiliation: Xiamen University, Affiliation: Washington University in St. Louis +2
Converts real repositories into verifiable, sandboxed training environments with black-box tests to train coding agents on long-horizon program reproduction. Provides Program-Env for automated environment construction and Program-Agent for a role-isolated development workflow, yielding 1,648 C/C++/Go/Rust tasks and improving benchmark performance.