norgitov/ trends
Technology · people · ideas
RSS
RUEN
Back to discovery/Daily Papers9 hours ago
ResearchDaily Papers

Scaling Agentic Data for Long-Horizon Terminal Intelligence

The paper introduces TerminalHorizon, an automated data synthesis engine for long-horizon terminal agents. It constructs 1.5K task environments and fine-tunes Qwen3.5-27B to create TerminalHorizon-27B, achieving performance gains across multiple benchmarks. The model demonstrates improved ability to experiment, refine methods, and retain effective improvements in final results.

Open original
SIGNAL FROM THE SOURCE
103
source votes
Tracking sinceOctober 13, 2026103 source votes

This source has not updated recently. Its observation time is shown above.

Momentum+5.93/hover 3.03 h
Discussion—Read comments ↗
PublishedOctober 9, 2026Shun Zou, Ziyu Ma, Yi Zou
BEHIND THE NUMBERS

How interest changes

Daily Papers

History starts here

The chart will appear after repeat observations. The current metric comes from the source.

103 source votes

Real observations only. History before source connection is not reconstructed.

WHY IT MAY MATTER

TerminalHorizon-27B can be used to improve autonomous task completion in real-world professional settings by enhancing the agent's ability to explore, adjust strategies, and refine methods based on feedback.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
Daily Papers

Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition

The study explores Adversarial Heuristic Learning (AHL), where AI agents refine game strategies with fixed model weights. The AAArena benchmark includes 12 games and 1,920 archived programs, evaluated through protocols mimicking real competitions. Results show agents can improve strategies but face challenges in complex games.

5 days agoDaily Papers

AgentSWE: Can Coding Agents Build the Agent You Actually Want?

The study presents AgentSWE, a benchmark evaluating coding agents' ability to build agents aligned with user requirements. The research found that existing agents fail to accurately fulfill tasks, as there is a significant gap between demonstrated and actual performance.

4 days agoDaily Papers

S-Space: Exploring Spatial Workspace in Multimodal Language Models

The paper introduces S-Space, a linear subspace in multimodal language models where object-token representations encode continuous spatial coordinates. It demonstrates that S-Space serves as an internal workspace for spatial reasoning, enabling accurate spatial judgments through perception, internal reasoning, and selective verbal access, while highlighting limitations in spatial transformations across viewpoints.

4 days agoDaily Papers

VIS-Ground: Video Interactive Storytelling with Contextual Grounding

VIS-Ground is a method that transforms heterogeneous input context into an executable constraint model for video generation using structured context abstraction, generation constraints induction, and constrained video generation. The approach demonstrates improvements over existing systems.

6 days agoDaily Papers

Tetris3D: 3D Scene Generation With Objects That Fit Together

Tetris3D is a generative framework for 3D scene reconstruction from a single image, ensuring objects are geometrically and physically coherent. It uses explicit conditioning on surrounding objects' geometry and physical relationships, along with a physics-based dataset called ComOb for training and evaluation.

6 days agoDaily Papers

Multi-Stream Attention Residuals

Multi-Stream Attention Residuals (MSAR) extends the AttnRes method by generalizing the attention mechanism to multi-head depth, achieving significant performance improvements with minimal additional overhead. MSAR leverages multi-scale causal convolutions to draw stream diversity from sequence context, allowing different heads to retrieve historical representations through distinct contextual views.

4 days ago