Tag

SoL-Pi: Recursively Scaling Auto-Research Loops for Efficient Agent Harness

Finds token- and API-cost-saving harness mechanisms for long-horizon coding agents using automated recursive self-improvement; packages four surviving mechanisms (action fusion, context compaction, observation archiving, delegated reading) to cut recorded token traffic ~44.7–49.0% and API cost by about one third while preserving most capability.

An Empirical Study of Harness Design for Coding Agents

Measures how individual harness components—planning, action space, and context management—affect coding agents' success, cost, and behavior. Uses a modular harness across 176 matched settings on SWE-Bench Verified and Terminal-Bench 2.1 to isolate component effects and surface model- and budget-dependent trade-offs.

JEPA-Anything: Learning Predictive Models across Different Worlds

Provides a domain-agnostic world-modeling framework that factorizes latent targets into orthogonal predictive components, with dedicated prediction branches and synthesis for multi-domain forecasting and intervention. Demonstrates improved dynamics and long-horizon rollouts across seven domains and includes experimental biological validation.

Spatial-Interactor: Learning Spatial Reasoning through Interaction with the Observable Physical World

Teaches vision-language models to predict and integrate physical-world state transitions from interaction trajectories (observation → action → next observation). Introduces a three-level curriculum and the LSI-108K dataset, and applies supervised fine-tuning plus on-policy distillation to improve local transition modeling and long-horizon spatial integration.

MiMo-V2.6-Flash-RL

A sparse-MoE multimodal LLM fine-tuned with large-scale mixed reinforcement learning, supporting text/image/video/audio and a 1M-token context window; designed for long-horizon agentic tasks, coding and visual reasoning with groupwise grading and on-policy distillation.

CLM-v0.1-8B

Scores candidate actions against a textual state using contrastive state/action embeddings for very fast zero-shot ranking and typed decision-making. Built as two small projection heads on frozen Qwen3-8B; fine-tunable as a verifier for agentic benchmarks.

MiMo-V2.6-Pro-RL

Open-weights multimodal LLM checkpoint designed for 1M-token long-context agent runs that combines large-scale on-policy RL with groupwise grading for iterative self-improvement. Key traits: sparse MoE backbone (≈1.02T total / 42B active), text-only output with image/video/audio inputs, MIT-licensed weights on HuggingFace—suited for long-horizon agents and research at significant infra cost.

WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory

Learns a camera-queryable implicit 3D-aware memory that compresses multi-view history into target-view tokens to enable long-horizon, camera-controllable video generation. Improves revisit consistency and camera-control accuracy and supports streaming exploration from a single image or text prompt.

GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay

Provides a unified data and evaluation suite for measuring gameplay capabilities across short, medium, and long temporal horizons. Includes an automated annotator, a 5,000-hour AAA gameplay dataset with temporally aligned frames, actions and multi-horizon instructions, and a reproducible offline + stepwise online benchmark.

Agent-Editing World Model: Rethinking World Modeling for LLM Agents

Edits an LLM agent's internal task state and action continuations to remove unsupported assumptions and noisy plans, improving downstream decisions instead of reconstructing high-entropy tool outputs. Combines Action Judge, State Revision, and EditAct and shows consistent gains across benchmarks and agent backbones.

The Past Frames the Future: Memory for Autoregressive Video Generation

Surveys memory mechanisms for autoregressive video generation, framing memory as persistent historical information that influences future generation. Organizes work by Forms, Functions, Operations, Learning, and Evaluation, and synthesizes challenges for long-horizon consistency and memory-aware learning.

Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents

A mobile-planning agent paper that develops a closed-loop AI-for-AI lifecycle to generate data, train a planner model, and co-evolve a runtime Harness for multi-app task execution. Demonstrates top performance on MobilePA-Bench with improved tool use, memory, skill coordination and low estimated per-task output cost.