Research Papers LingBot-World 2.0 upgrades the game world model to an unbounded interaction horizon with consistent output quality via a causal pretraining paradigm, distills a real-time variant fast enough to drive 720p video at 60 fps, and greatly expands the action set (attacking, archery, spell-casting, shooting) plus text-driven interactive elements.
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.
Apodex 1.1 targets what the authors call working capability: it scales up the diversity and verifiability of executable file, search and code environments, while training agents to decompose long-horizon tasks, delegate parallel work and integrate asynchronous results.
Dream-RSI is a framework for letting coding agents improve their own exploration strategy instead of keeping a fixed one. It builds a replay simulator from the agent's past discovery trees, lets the exploration policy practice inside that simulator for cheap off-policy feedback, then redeploys the refined strategy online so new discoveries feed the next round. The authors report competitive or better discovery quality on algorithm engineering, math optimization, and GPU kernel tasks, with substantially lower discovery cost in several settings.
ABot-World-0 is an action-conditioned video world model trained on multi-source data from AAA games, simulation engines and internet videos, controlled through raw keyboard input with reference-character memory for consistent third-person rollouts. The authors report streaming 720p at up to 16 FPS on one RTX 5090 with 1.2s action-to-first-frame latency, targeting real-time long-horizon closed-loop interaction.
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.
Atria Dawn introduces a foundation agentic language model built for scientific research and engineering workflows. Its training pipeline, which the authors call the Verifiable Experience Pipeline, ties tool-mediated interactions to executable environments and externally checked outcomes; the paper also studies human-AI collaboration using 769 task records from 56 researchers working with the agent.
OSWorld 2.0 from the xlang-ai team replaces short scripted tasks with 108 long-horizon computer-use workflows built on authentic artifacts and stateful user profiles; humans take a median of about 1.6 hours per task. The headline finding is how far agents still are: the best model, Claude Opus 4.8, completes only 20.6% of tasks, often losing track of constraints or skipping verification.
LLM-as-a-Verifier turns a language model into a verifier by computing expectations over its scoring-token logits instead of prompting for discrete judgments, yielding continuous feedback with no extra training. The authors report state-of-the-art results on benchmarks including Terminal-Bench V2 and SWE-Bench Verified, and ship a Claude Code extension that watches agents and supplies dense rewards for RL.
ZGCM-1 is a fully open 7B dense foundation model aimed at math reasoning and agentic search. The idea is that a smaller model cannot memorize the whole web, so it couples long internal thinking with active tool use, using interleaved gated sliding-window and full attention, an FP8 Muon optimizer, and curriculum training that scales context to 256K. The authors say they release stage-wise weights, training code, per-stage data recipes, and W&B logs.
This survey decomposes a self-improving agent into a foundation model and an operational scaffold of prompts, memory, tools and control logic, then defines improvement as a self-induced update operator that converts experience into accumulated capability with minimal human input. It organizes the growing literature by update target and driving signal, from prompt and memory edits to weight-level self-modification.
SoL-Pi applies recursive self-improvement to the agent harness rather than the model: an automated research loop scaled across many environments discovers reusable mechanisms for action execution, context compaction, observation handling, and delegated reading. On the 51-task EdgeBench benchmark, the authors report matching Pi-level performance with 44.7-49.0% less recorded token traffic and roughly one-third lower API cost.
Long-Horizon-Terminal-Bench tests agents on 46 multi-step terminal tasks across nine areas, from reproducing experiments to scientific computing. Each task is decomposed into fine-grained subtasks so agents earn partial credit for intermediate progress, and the authors report that frontier models still solve only a small fraction of runs.
WeMM-Embedding is a family of universal multimodal embedding models (2B, 4B and 9B) covering text, images, video, visual documents and arbitrarily interleaved inputs, with flexible output dimensions, trained by large-scale alignment followed by refinement with curated relevance supervision.