AI ToolsBharatHunt Trend Score22
Rubrics from the Task, Verdicts from Evidence: Pointwise Rubric Rewards with Tool-Augmented Judges
Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI Intelligence Hub
What’s Trending in AI?
Discover the latest AI news, tools, models, launches and trends shaping the future.
Results for “Reasoning Models”
317 stories · best match
Last updated 6 hours ago
AI ModelsBharatHunt Trend Score23
OVAL: Output-Aware Local Page Bases for KV Cache Retrieval
It centres on Inference, and also names Benchmarks and GitHub. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI AgentsBharatHunt Trend Score21
GRASP: Generating, Revising, and Assessing for Strategic Planning with Agentic AI
It centres on Reasoning Models, and also names GPT. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ModelsBharatHunt Trend Score22
Real PMIDs, Wrong Papers: Harness Design for Biomedical Claim-Verification Agents
The story centres on GitHub. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ModelsBharatHunt Trend Score20
Einride expands Nvidia partnership to deploy AI reasoning model for self-driving trucks
It centres on NVIDIA, and also names Reasoning Models. Reported by The Economic Times.
Source: The Economic TimesRead original(opens The Economic Times)
AI CodingBharatHunt Trend Score22
PreciseCoder: Faithful and Generalizable Debugging Beyond Unit-Test Rewards
The story centres on GPT. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ModelsBharatHunt Trend Score21
Learning to Act with Task Progress: Distilling Small Agents from Compact Teacher Supervision
Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ModelsBharatHunt Trend Score21
GAGR-Lab: Evaluating Joint Spatial-Geometric and Analytic Function Reasoning
The story centres on Llama. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ResearchBharatHunt Trend Score21
Debias It Yourself: Teaching LLMs Cognitive Bias Mitigation Interventions
The story centres on Benchmarks. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ModelsBharatHunt Trend Score21
SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
It centres on Benchmarks, and also names GitHub. Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ResearchBharatHunt Trend Score22
Base Models Can Reason By Taking a Cue From Training Data
Reported by arXiv.
Source: arXivRead original(opens arXiv)
AI ModelsBharatHunt Trend Score24
Distillation Defenses Easily Break After Reinforcement Learning
The story centres on Replicate. Reported by arXiv.
Source: arXivRead original(opens arXiv)