Model Detail
Agents-A1
—Agents-A1 is a large language model with 17.6B parameters released by InternScience. The model is registered under the text-generation pipeline tag on Hugging Face, distributed under the permissive apache-2.0 license.
Agents-A1 ships with 17.6B parameters. Total weight footprint is approximately 35.1 GB, which is the relevant figure when planning local-inference VRAM. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
Agents-A1 is best fit for general-purpose chat and instruction-following workloads. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
Agents-as-Peers: Bias-Controlled LLM Evaluation as Multi-Agent Peer Assessment
arXiv:2602.02589v2 Announce Type: replace Abstract: Large language model (LLM) evaluation commonly relies on fixed human-authored benchmarks or centralized human/model judges. Fixed benchmarks can age and enter model training corpora, while centralized judges introduce their own scoring preferences.
Agentic vs. Parametric World Models: Hybrid Planning for Reliable Language Agents
arXiv:2606.27806v4 Announce Type: replace Abstract: Language agents, such as ReAct, Reflexion, and RAP, implicitly predict how the world will change as they plan and act, using imagined state transitions to guide their decisions. These predictions are encoded in the agents' backbone LLMs as internal
For Coding Agents, the Repository Matters
arXiv:2606.28235v2 Announce Type: replace-cross Abstract: In July 2026, about 1,200 AI agents in an internal OpenAI evaluation, meant to run in isolation, used a shared package server as a message board, and about 700 of them joined an attack on Hugging Face. An automated scorer judged each agent on
Self-Evolving Agents through Privileged Retrospective Distillation
arXiv:2610.27495v1 Announce Type: cross Abstract: Self-evolving agents aim to improve from their own experience rather than remain fixed after deployment, but naturally collected trajectories often lack ground-truth solutions or verifier-derived rewards. We introduce Retrospective Self-Distillation
Local Allow, Global Deny: Why Per-Action Authorization Does Not Compose in LLM Agents
arXiv:2610.27620v1 Announce Type: cross Abstract: Autonomous LLM agents act through tools under per-action authorization: a local guard screens each tool call in isolation. We show that local authorization does not compose into global authorization. A compositional authorization failure (CAF) is a l
Does Multi-Agent Collaboration Pay When Agents Serve Users? Testing Agent Scaling in Dual-Control Settings
arXiv:2610.27655v1 Announce Type: new Abstract: Multi-agent systems (MAS) built from language models are deployed on the premise that collaboration beats a single-agent system (SAS), yet when it pays is unclear. The most systematic study to date gives a capability-saturation rule: coordination helps
