9 Oct 2026
LLM agents' capabilities depend not only on their underlying models but also on their execution harnesses. Recursive self-improvement (RSI) offers a promising approach to automatically evolve these harnesses.
Trending research and the full catalog - each paper linked to the benchmarks, methods, and models it introduces.
Filtering here covers the 2,000 most recent papers, as much as one page can hold in memory. See the full index of 23,060 papers.
9 Oct 2026
LLM agents' capabilities depend not only on their underlying models but also on their execution harnesses. Recursive self-improvement (RSI) offers a promising approach to automatically evolve these harnesses.
8 Oct 2026
Reinforcement learning (RL) is the central training paradigm for advancing large foundation models towards self-improvement. This report introduces the MiMo-V2.6 series, an omni-modal family that pushes the frontier of model intelligence by scaling RL compute.
26 Oct 2026
As foundation models evolve from information generation to digital work execution, agents are increasingly capable of completing complex tasks across tools, applications, and workflows.
14 Jul 2026
Self-improving autonomous agents are moving from research prototypes to deployed systems. The primary goal is controllable evolution, or adaptation, from experience with minimal or even no human input.
18 Jun 2026
Agent benchmarks are growing fast, but no single benchmark touches more than four or five of the dimensions that deployment exposes. This paper aggregates the largest coordinated deep-dive of one MCP-based industrial-agent benchmark to date: fourteen parallel implementation…
5 Jul 2026
Large language models have made research ideation increasingly accessible, yet effective idea development requires more than generating candidate directions. Researchers must ground a problem in current literature, identify meaningful bottlenecks, differentiate from existing…
20 Oct 2026
Scaling data, diversity and model capacity has improved embodied learning in physical environments, where diverse experiences remain grounded in shared physical laws. Whether these gains extend to virtual worlds with different visual styles, dynamics, controls, and objectives…
12 Aug 2026
Software systems accumulate dependencies and design commitments over time, while the agents that modify them operate within bounded sessions. How, then, can development remain cumulative across generations of transient agents? We introduce EvoX Genesis, which organizes…
4 Aug 2026
Human evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but often abstract away human diversity and interactive behavior.
14 Sep 2026
Recursive self-improvement is becoming essential for autonomous AI agents, whose progress depends on discovering high-value solutions across complex domains. Effective exploration drives this process, yet managing and improving exploration strategies remains a major bottleneck.
27 Sep 2026
As large language models advance, AI agents are moving beyond isolated, domain-specific tasks toward long-horizon, cross-domain workflows. This transition exposes two challenges: increasing harness complexity makes manual design difficult to scale, while tighter coupling to…
28 Jun 2026
Skills are a useful abstraction for software agents, turning human and agent experience into reusable procedural knowledge. Yet existing skill libraries are mostly hand-written, text-centric, or derived from agent traces, leaving tutorial videos and other multimodal human…
13 Oct 2026
Harness self-evolution revises an agent's software scaffolding, including prompts, memory, workflows, and executable components, while keeping model weights fixed. We formalize a feedback-driven process in which accepted revisions persist across runs.
6 Oct 2026
Assistants from 2011 answered and waited, and agents from 2023 did a task and stopped. In September 2026 Meta's Muse showed an agent for one person, with accounts, devices, memory and a conversation that lasts, closed, in a vendor's cloud, in one country.
6 Jul 2026
For robots to work reliably in commercial and industrial applications, recent advances in agentic coding systems have potential to combine interpretable robot programming with the open-world adaptability of model-free policies.
28 Oct 2026
We introduce Nemotron 3.5 Super and Nemotron 3.5 Lightning, open and efficient Mixture-of-Experts Hybrid Mamba-Transformer models designed for reasoning, long-context understanding, and agentic workloads.
29 Oct 2026
As publications and products on time series forecasting (TSF) proliferate, researchers face a growing burden of analyzing existing work. First, not all publications release code. For instance, only about 20% of arXiv TSF papers have a code link in the surveyed period.
16 Nov 2026
Agentic artificial intelligence could automate analyses of sensitive clinical data, but current agents depend on large language models (LLMs). Cloud LLMs expose patient data. Local LLMs hallucinate, and an invented value in a tool call propagates through every later step.
16 Nov 2026
We present K2-Horizon, a fleet of six fully open language models, from a 0.9B dense model to a 375B-A23B MoE, built for general-purpose reasoning and agentic work across math and science, software engineering, deep research, office automation, and beyond.
9 Nov 2026
Long-term memory lets LLM agents personalize, stay consistent, and reuse what worked before. Parametric memories need training, consolidation can lose details for good, and keeping every record leaves a growing store to search.
30 Oct 2026
Agent harnesses govern how language models act in an environment; designing their policies by hand is difficult, while automated techniques require representative datasets and costly executions.
5 Nov 2026
Agent exploration produces valuable procedural knowledge, yet much of this experience remains confined to transient execution traces and is not systematically reused. We introduce Evolver, an experience-driven framework that transforms agent exploration into persistent, reusable…
2 Nov 2026
Rapid advances in cowork agents are shifting human-AI collaboration toward real-world automation, delivering software, designs, and other artifacts. However, such productivity work demands both high-quality delivery on complex productivity tasks and continued monitoring and…
16 Nov 2026
Visual agents answer questions about ultra-high-resolution photos by zooming into the relevant regions. However, existing agents often answer from common sense instead of reading the evidence.