AI Agent Papers2024
Treats the interface between an LM agent and a computer as a design variable. A custom agent-computer interface (ACI) with concise file-edit, repo-navigation, and test commands plus compact feedback reaches 12.5% pass@1 on SWE-bench, 87.7% on HumanEvalFix.
Chops any layer-sequence model across accelerators and splits each mini-batch into micro-batches to keep the pipeline busy, hitting near-linear speedup without architecture-specific tricks or fast interconnects.
Enforces output grammars during LLM decoding while reducing CPU validation overhead. Precomputed token masks and persistent stacks support nested formats without checking the full vocabulary at every step.
Standardizes representation-level evaluation for tabular encoders by exporting row-, column-, and table-level embeddings and probing them with shared lightweight heads across three suites (TRL-CTbench, TRL-Rbench, TRL-DLTE). Supplies curated benchmark assets and task rewrites (50 OpenML tables, 123 targets, a 47,772-table DLTE lake) to enable fair cross-paradigm comparison.
Embodied AI2026
Provides a portable C++ inference runtime to deploy embodied AI models (vision–language–action and world–action) on heterogeneous robot hardware, enabling latency-first batch-1 closed-loop control. Key features include modular multi-rate layers, fused low-latency inference, and extensible head/IO plugins.
Autonomously proposes, modifies, executes, and evaluates ML experiments to study recursive self-improvement in machine learning engineering. Implements an open stack (OpenMLE-Gym, -RL, -Evo) and post-trains Frontis-MA1 (35B) around four evolution operators (Draft, Improve, Debug, Crossover); releases model weights and the full codebase.
A pretrain-then-transfer method for streaming recommendation that decouples refreshable behavioral knowledge from task-specific geometry to enable continual model refresh without downstream interference; introduces Behavioral Multi-Token Prediction and Anchored Calibration Residual and shows 4–12% offline gains plus live Shopee A/B lifts.
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
Defines and evaluates AREX-2, an LLM agent that iteratively self-improves at test time via reflection and long-horizon execution. Trained on long-horizon improvement trajectories from ML engineering and algorithmic programming (built on Qwen3.8-27B), it scales with more rounds and achieves strong benchmark scores.