arXiv Research Papers | Pulsar - Daily AI/ML Paper Digest

🤗 HuggingFace Daily Papers

Scientific code repositories encode decades of human knowledge in executable models, methods, and tools.
Yet fragmented toolchains, implicit domain conventions, and specialized correctness criteria make this knowledge difficult to convert into reliable le...
We introduce ScienceIDE, infrastructure for turning the world's scientific code into programmable environments for scientific agents.
Guided by expert-defined scientific cases and acceptance criteria, agents transform repositories into executable environments that support task genera...

We introduce LimiX-2, a new model in the LimiX family, developed through model and data scaling guided by our previously established scaling laws.
LimiX-2 adopts the Contextual Mechanism Networks (CMNs) paradigm and is pretrained with Context-Conditional Masked Modeling (CCMM).
CMNs shifts the organizing principle of in-context learning from target-centric prediction to mechanism-oriented joint modeling.
Rather than centering the network on the p(y mid x, D_{context}) objective of conventional tabular PFNs, it is designed around learning p(x, y mid D_{...

In reinforcement learning for large language models, Proximal Policy Optimization (PPO) commonly uses a critic to estimate state values and reduce the...
However, we uncover a systematic failure mode in PPO critics, which we call Value Flattening: state values, estimated from multiple Monte Carlo contin...
We further observe this phenomenon in a controlled FrozenLake environment and find that it becomes more pronounced as the state space grows.
Our theoretical and empirical analyses relate Value Flattening to an implicit variance penalty in the critic loss and redundant updates from temporall...

Reliable confidence estimation is increasingly central to the trustworthy deployment of language models: a calibrated estimate of the probability that...
Existing confidence estimators, however, share one design premise: they only read the current inference process, either by introspecting on it, scorin...
We argue that the current inference is not a sufficient basis for confidence.
We propose XConf (eXperiential Confidence): estimating confidence together with the model's accumulated experience.

Coding agents are typically evaluated with desired behavior specified through issues or instructions.
In practical web development, however, agents may need to infer behavior from working software and implement it in an incomplete application.
We introduce ProgramDistill, a benchmark evaluating coding agents on features discovered through interaction with fully functional reference applicati...
We build ProgramDistill by factorizing applications into features of different granularities, each associated with replayable behaviors executable via...

Action tokenizers play a central role in autoregressive vision-language-action (VLA) models, determining both the targets for policy training and the ...
Their fidelity is commonly evaluated using pointwise reconstruction metrics such as mean squared error (MSE), yet small individual errors do not fully...
After compression, similar actions may still cluster around a representative motion, while the adjustments needed for different contexts are diminishe...
We introduce physical rank consistency (PRC) to measure how well tokenization preserves local physical distance rankings after reconstruction.

Autonomous research loops such as AutoResearch show that one coding agent can improve a training setup unattended.
Run several of them and each session starts from scratch, so more agents tend to mean more duplicated search rather than more discovery.
Agora is a shared memory for such agents: research is recorded as an append-only directed acyclic graph (DAG) stored in Git, so that every claim is a ...
Each result, insight, hypothesis, verification, and report is an immutable commit whose parent edges say what it builds on; a derived index exposes th...

Large language model (LLM) trading agents can combine market data, news, and executable analysis, but their behavior is often controlled by static han...
This limits their ability to adapt how they gather evidence, invoke tools, verify signals, and manage risk under changing market regimes.
We introduce EvolveTrade, a self-evolving framework that treats the system prompt of a tool-using trading agent as a text-parameterized policy.
After each update interval, a Policy Agent revises this policy using accumulated decision traces and realized portfolio feedback, while keeping the ba...

🏛️ Top Research Institutions

LLM-based agents are rapidly deployed in production without systematic understanding of their quality assurance gaps and...
Large-scale empirical study characterizing QA practices, testing strategies, and identified gaps across AI agent impleme...

AI & Machine Learning

447 papers 7 cats

Systems & Infrastructure

47 papers 6 cats

Software & Programming

10 papers 4 cats

Theory & Algorithms

16 papers 5 cats

Applications

157 papers 7 cats

Other CS

3 papers 9 cats