Tag
This paper introduces BitCal-TTS, a runtime controller that improves accuracy and reduces premature halting in quantized reasoning models by calibrating confidence signals during test-time scaling.
Stream-T1 is a proposed framework for test-time scaling in streaming video generation, improving temporal consistency and quality through mechanisms like noise propagation and reward pruning. The paper addresses the high computational costs of existing diffusion-based methods by leveraging chunk-level synthesis.
FS-Researcher introduces a file-system-based dual-agent framework that enables LLM agents to conduct deep research beyond context window limits by using persistent external memory as a shared workspace. The framework achieves state-of-the-art results on research benchmarks and demonstrates effective test-time scaling through computation allocation to evidence collection.
AgentV-RL introduces an Agentic Verifier framework that enhances reward modeling through bidirectional verification with forward and backward agents augmented with tools, achieving 25.2% improvement over state-of-the-art ORMs. The approach addresses error propagation and grounding issues in verifiers for complex reasoning tasks through multi-turn deliberative processes combined with reinforcement learning.
Academic study shows LLM agents frequently discover complete solutions in their environments but almost never use them, revealing a missing "environmental curiosity" capability critical for open-ended tasks.
A test-time scaling framework for agentic coding that compresses rollout trajectories into structured summaries and uses recursive voting/PDR to boost Claude-4.5-Opus to 77.6% on SWE-Bench Verified.