90 days of the enterprise, pro and team plans free, no card needed. See the plans
Blog
Daily notes on new models, LLM releases, agent frameworks and AI research, written from the sources we follow and delivered as a newsletter every day.
Get the morning and evening issues
Every new post of the day, in one email. Confirmation required.
LLMs1 min read
A new pipeline synthesizes 90k multimodal samples to enable scalable Reinforcement Learning with Verifiable Rewards, improving instruction-following by 8.13%.
From arXiv cs.CL
LLMs1 min read
A new framework uses an 8B model to generate charts matching human visual standards through iterative self-reflection and reinforcement learning.
From arXiv cs.CL
Photo: Yan Krukau
LLMs2 min read
A new study finds few-shot prompting effects vary by task and are driven by demonstration content rather than prompt length. Replacing demonstrations with random text isolates the impact of representation shifts caused by content.
From arXiv cs.CL
LLMs1 min read
A retrieval-augmented generation framework extracts crash mechanisms from narratives to recommend site-specific traffic safety countermeasures. Evaluated on 312 fatal crashes, it achieved an F1-score of 0.82 with LLMs guided by engineering reasoning.
From arXiv cs.CL
LLMs2 min read
arXiv:2609.16340v1 Announce Type: new Abstract: Machine translation systems are periodically upgraded to stronger models, but the available preference signal is human post-edits of an older system's outputs, which the newer model may alr...
From arXiv cs.CL
LLMs1 min read
A new study finds that non-atomic and rigid criteria in clinical benchmarks can artificially inflate or deflate LLM evaluation scores, with rewriting disjunctive bundles shifting results by up to 15.9 percentage points.
From arXiv cs.CL
LLMs2 min read
Research shows ordinary typos rotate hidden state vectors by 43 to 56 degrees, causing prompt injection probes to drop true positive rates by up to 12 percentage points.
From arXiv cs.CL
Research1 min read
arXiv:2609.13406v1 Announce Type: new Abstract: When we speak of recursive self-improvement (RSI), are we speaking of a phenomenon, a mechanism, or a prospect? Towards autonomous and evolving intelligence, RSI is being claimed at many sc...
From arXiv cs.AI
Research1 min read
arXiv:2609.13566v1 Announce Type: new Abstract: Industrial maintenance systems involve multiple interacting assets and shared resources, making it challenging to balance reliability and operational cost using a single decision framework....
From arXiv cs.AI
Research1 min read
arXiv:2609.13422v1 Announce Type: new Abstract: LLM judges are increasingly used to evaluate and improve AI-generated outputs, yet their reliability for complex professional work remains unclear. We study this problem through Vibe Patent...
From arXiv cs.AI
Research1 min read
arXiv:2609.13463v1 Announce Type: new Abstract: The increasing deployment of AI agents in long-horizon tasks yields massive execution logs. Diagnosing failures within these records is crucial for reliability, as it transforms outcome-lev...
From arXiv cs.AI
LLMs1 min read
arXiv:2609.13556v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown remarkable proficiency on general-purpose tasks, yet their performance often degrades in highly-specialized technical domains. Moreover, little is kn...
From arXiv cs.CL
LLMs1 min read
arXiv:2609.13582v1 Announce Type: new Abstract: A clinical agent benchmark can report the same verdict on identical inputs while the agent files a materially different order on each run. Such agents order tests, request medications and p...
From arXiv cs.CL
LLMs1 min read
Research demonstrates that distilled byte models, utilizing Marginalize-It and End-Of-Token methods, outperform token models in low-FLOP regimes. The study reveals that byte models achieve higher downstream task performance with increased compute, offering improved data efficiency and reduced storage costs.
From arXiv cs.CL
LLMs1 min read
Research reveals a significant disconnect between LLM-as-a-judge rankings and actual task success in user-simulated evaluations of task-oriented agents. The study, GAUGE, identifies a satisfaction-success gap and resolution loss among closely-ranked agents, highlighting the need for a calibrated approach to agent selection.
From arXiv cs.CL
LLMs1 min read
The ESTS team achieved parameter counts between 4.186B and 7.770B and artifact sizes between 4.55 and 6.33 GiB across six submissions for the WMT26 Model Compression Shared Task.
From arXiv cs.CL
Research1 min read
Research indicates that large language models are inadequate for consequential quantitative decisions like risk pricing or network intrusion containment. The paper proposes Large Quantitative Models (LQMs) that address key limitations regarding reproducibility, lineage, and calibrated uncertainty.
From arXiv cs.AI
LLMs1 min read
The R2VC architecture, combining retrieval, verification, and confidence calibration, achieves higher accuracy in open-domain fact-checking compared to baseline models. Ablation studies highlight the critical roles of candidate selection and confidence calibration in improving both predictive accuracy and reliability.
From arXiv cs.CL
Research1 min read
This paper introduces Affective Agent, a three-layer architecture for personalized intervention reasoning on wearable devices. The system uses a compact language model and physiological data to make intervention decisions without cloud dependency, improving closed-loop systems.
From arXiv cs.AI
Posts are drafted from public feeds by models OpenSmartRoute routes to - the same router, skill and metering customers use - and always link to the original source. Corrections: support.
Archive (100)
