Research Papers FreeToken rethinks local inference around two realities of edge AI: agent workloads keep changing shape, and every machine's resource balance differs. It co-designs model layout, expert residency, CPU-GPU execution and memory management instead of committing to a fixed offloading strategy.
Prime Agent is an open harness for long-horizon coding agents built on the Recursive Language Model idea: a persistent IPython session does test-time computation, while histories, memories, skills and subagent specs carry over between runs.
Ouroboros is a self-developing coding-agent harness whose tools, prompts, context assembly and even core implementation improve through reviewed commits that become its later runtime, with two evolution modes: recursive free evolution and experience-driven core evolution. The authors also report a 161-day live deployment across seven human communication surfaces, arguing safety guardrails must stay authoritative while the agent rewrites its own code.
This harness maintains an explicit task state outside the agent's execution context and updates it only with facts independently verified from the environment, using a Manage-Execute-Audit loop so mistaken self-assessments do not snowball across many steps.
AutoDesign treats multimodal conference-poster generation as a long-horizon agentic process: a meta-harness optimizer reads rollout feedback and rewrites the harness the code agent runs on. On the authors' 100-paper PosterBench it scores above Claude Design, the learned harness lifts seven different code-agent configurations, and a fully autonomous loop makes 253 tool calls in 40 minutes for under $3.
After Meta's closed Muse demo showed what a single-person agent with lasting memory could look like, this report reconstructs how Muse is built from public sources, then ships nanoMuse as its GPL-3.0 open counterpart: one agent across the devices you own, sharing a single conversation over a relay anyone can self-host. Every action passes a Sentinel gate before it executes, memory is stored as plain files the owner can read, and the underlying model is the user's choice.
MOSS-Image is an open generation system aimed at the gap where open-weight image models still struggle with dense text and intricate layouts. It pairs a 5B single-stream diffusion transformer pretrained from scratch, which the authors say enables bilingual long-form text rendering and precise layout control, with an intention-aware agentic prompt enhancement module that turns loose user requests into detailed content and layout specifications. The report introduces two new benchmarks, LongLongTextBench and RealLayoutArena, and reports that MOSS-Image is state of the art among open-weight models on long-form English and Chinese text rendering with 96.3% average text coverage, and ranks second in end-to-end layout-rich generation. The authors say they will release the model, training recipe, and evaluation framework.
Raven argues that hand-crafted agent harnesses are too domain-coupled to scale with long-horizon, cross-domain workloads. It treats each model–harness pair as a composable unit of intelligence: a Host Agent decomposes goals and coordinates specialized sub-agents, a host archive and EverOS retain experience across tasks, and Skill Forge turns that experience into reusable procedures — with theory on expanding reliable task coverage under one resource budget.
OpenGCUA rebuilds the computer-use agent stack in the open, motivated by the observation that frontier systems like GPT-6 Astra's computer use are closed. Its core idea is to let the model choose between visual GUI actions and direct code execution, so intermediate results can steer later steps; it also proposes harness-to-model decision transfer, moving selected observation and task-state decisions out of fixed harness rules and into the model itself. The authors report that on OSWorld-v2 their full configuration improves task scores across all eight evaluated models (including GPT-6 Astra and Claude Opus 5), raising mean partial score by +19.6 points and cutting reported steps per task by 53.0% on average versus batched GUI-only execution. Alongside the implementation and prompts they release evaluation trajectories from all eight models, plus early versions of a real-device harness and a cross-device SDK covering computers, mobiles, and browsers; on four real macOS tasks their harness shows selected Qwen3.8-Max runs use 19.4 times as many reported reasoning tokens as GPT-6 Astra, which they highlight as a gap in real-device execution efficiency.
This paper evaluates GPT-6-Astra as a general embodied agent rather than a robot-specific model, running it across 12 benchmarks covering tabletop manipulation, humanoids, mobile platforms, and dexterous hands, plus 8 real robot setups. The authors find that with in-context demonstrations and longer execution horizons it shows broad competence, but report that a System 2 reasoner paired with a low-level controller is expensive, that demonstration collection is costly, and that failures often come from irreversible physical mistakes rather than reasoning. Their conclusion: GPT-6-Astra has largely crossed the threshold of embodied competence, but not yet practical embodied intelligence, and they sketch a harder next-generation benchmark built from real needs.
MemT-1.0 is a family of memory foundation models (Nano and Flash) that make memory an internal computation step instead of stuffing past context into the prompt: built on the Metis architecture with Gated DeltaNet-2 and a Mixture-of-Storage layer, the model updates token-level memory within each turn. The authors report it beats parametric-memory baselines on average, stays competitive with retrieval-augmented methods, and at 128K-token history it achieves about 1.86x end-to-end inference speedup with 66x less persistent storage than keeping the full KV cache.
This 66-page position-style paper formalizes harness self-evolution: an agent keeps its model weights fixed but continually revises its own software scaffolding, including prompts, memory, workflows, executable components, and plugins. Accepted revisions persist across runs, and the authors separate what can be updated from the proposal and admission mechanisms, analyzing reliability with PAC-learning-style bounds and an admission rule that requires fresh independent validation data. The paper argues this demands continual validation plus independent safeguards on runtime privileges and consequential actions.
Making a long film with a video-generation agent breaks down at the seams: passing prompts or a few recent frames between shots gives the model neither a shared spatial frame for revisiting a scene nor a time-indexed record for replaying an earlier event. ATAS compiles a screenplay into shot requests with explicit location, camera, and event-time references, and keeps two memories behind the generation loop: a scene memory of registered static geometry and an event memory of dynamic observations indexed by scene, event, and time. Each generated clip is reconstructed and registered back, admitted only after review and state checks. The authors report that this improves all measured cross-shot consistency metrics across four video generators, outperforms compared agents and 3D-guided methods on spatial revisits and event recapture, and earns the highest human ratings on all six evaluated criteria.
Scaling laws are well established for language models in the physical world, but do they hold for embodied agents acting in virtual worlds with different graphics, physics, controls, and objectives? This paper runs a controlled study of continued pre-training across three axes, with 120 configurations spanning four model sizes (0.8B to 27B), six data budgets (50 to 1,600 hours), and five data mixtures from Minecraft-only to diverse multi-world corpora. The findings: more data helps within the training worlds, data diversity transfers to related worlds but barely to distant ones, and larger models use data more efficiently yet generalize worse to distant worlds under single-world training. Training also splits into an early interface phase with broad cross-world gains and a later world phase where gains narrow to familiar worlds. The authors fit an empirical scaling law relating validation loss to volume, diversity, and size, and note that persistent gaps in distant worlds mean generalist embodied agents will need training stages beyond continued pre-training.
This survey organizes in-context learning for robotics around one question: how can a robot pick up a new task from demonstrations or interaction while its network weights stay fixed at deployment? It groups the literature into four families based on how context connects to execution: context-conditioned policies, geometric demonstration transfer, world-model-based control, and skill- or agent-based execution, then compares their transfer assumptions and how training, correspondence and memory make the context useful. It also reviews evaluation practices that separate responsiveness to teaching, physical transfer, and gains from retained experience, and closes with a research agenda toward physical recursive self-improvement. A companion GitHub repo collects the papers.