Interleaves chain-of-thought reasoning with tool-using actions in one LLM loop: the model plans, queries a source like Wikipedia, then revises from results. Cuts hallucination versus reasoning-only prompting and beats trained agents on interactive tasks.
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.
An open large language model pairing DeepSeek Sparse Attention (DSA) for cheaper long-context inference with a scaled RL pipeline. Authors claim parity with GPT-5, with a high-compute Speciale variant surpassing it and rivaling Gemini-3.0-Pro on reasoning.
Combines internalizing general skills with task-specific skill utilization via a difficulty-aware router to improve in-distribution and out-of-distribution performance for agentic RL. Uses privileged distillation for hard tasks and diagnostic probing for easy tasks; evaluated on ALFWorld and WebShop.
AI Agent Papers2026
Proposes TASTE, an automatic pipeline that synthesizes challenging agent benchmark tasks by sampling and evolving valid tool-sequence patterns; uses an adaptive contrastive n-gram model and LLM validity judgments to produce τ^c-Bench with broader tool-use coverage and higher difficulty.
AI Agent Papers2026
Analyzes when masking stale observations improves long-horizon search agents and why, identifying an asymmetric inverted-U relationship between masking benefit, retriever quality, and model capacity; explains a token-for-turn trade-off and releases evaluation scaffolds and trajectories.
AI Agent Papers2026
Automates distillation of heterogeneous traces from a target person or role into versioned, inspectable skill packages for LLM agents — producing separate capability and bounded-behavior tracks that support natural-language corrections, rollback, and cross-host installation. Ships with an open system and a skills gallery.
AI Agent Papers2026
Localizes harmful span-level errors inside long research-agent trajectories to show which trajectory segments make final answers unreliable. Provides a 1,000-instance TELBench of annotated spans and DRIFT, a claim-centric auditing method that improves span-level localization and first-error accuracy by up to 30 percentage points.
A 20B retrieval subagent trained with reinforcement learning inside a stateful search harness that externalizes recoverable search state (candidate pool, curated evidence, verification records). The harness lets the policy focus on semantic search decisions, improving curated recall and transfer robustness.
Omnimodal world model that jointly processes and generates text, images, video, audio, and action trajectories for physical AI. Uses a mixture-of-transformers to combine autoregressive reasoning and diffusion-based multimodal generation; released open-source with checkpoints, datasets and benchmarks for robotics and simulation.
AI Agent Papers2026
Workflow-aware benchmark for autonomous medical-AI research that splits agent execution into five stages (Plan, Setup, Validate, Inference, Submit) and evaluates long-horizon runs across segmentation, image enhancement, VQA, report generation, and lesion detection with stage-level scoring.
AI Agent Papers2026
A benchmark for evaluating web-browsing agents in Korean contexts, composed of 400 tasks (300 manually verified by native speakers). Includes a human-verified split and an adversarial synthetic split to probe failure modes; reveals large performance gaps for both frontier and Korean models.