Large Reasoning Models (LRMs) have achieved impressive performance on complex reasoning tasks by generating detailed chain-of-thought (CoT) explanations. However, these responses are often excessively long, containing redundant reasoning steps that inflate inference cost and reduce usability. Controlling the length of generated reasoning without sacrificing accuracy remains an open challenge. Through a systematic empirical analysis, we reveal a consistent positive correlation between model entropy and response length at different reasoning stages across diverse LRMs: the thinking phase exhibits higher entropy, reflecting exploratory behavior of longer responses, while the final answer phase shows lower entropy, indicating a more deterministic solution. This observation suggests that entropy at different reasoning stages can serve as a control knob for balancing conciseness and performance. Based on this insight, this paper introduces Phase Entropy Aware Reward (PEAR), a reward mechanism that incorporating phase-dependent entropy into the reward design. Instead of treating all tokens uniformly, PEAR penalize excessive entropy during the thinking phase and allowing moderate exploration at the final answer phase, which encourages models to generate concise reasoning traces that retain sufficient flexibility to solve the task correctly. This enables adaptive control of response length without relying on explicit length targets or rigid truncation rules. Extensive experiments across four benchmarks demonstrate that PEAR consistently reduces response length while sustaining competitive accuracy across model scales. In addition, PEAR demonstrates strong out-of-distribution (OOD) robustness beyond the training distribution. Our code is available at: https://github.com/iNLP-Lab/PEAR.

The ALPHA-g experiment at CERN aims to precisely measure the terrestrial gravitational acceleration of antihydrogen atoms. A radial Time Projection Chamber (rTPC), that surrounds the ALPHA-g magnetic trap, is employed to determine the annihilation location, called the vertex. The standard approach requires identifying the trajectories of the ionizing particles in the rTPC from the location of their interaction in the gas (spacepoints), and inferring the vertex positions by finding the point where those trajectories (helices) pass closest to one another. In this work, we present a novel approach to vertex reconstruction using an ensemble of models based on the PointNet deep learning architecture. The newly developed model, PointNet Ensemble for Annihilation Reconstruction (PEAR), directly learns the relation between the location of the vertices and the rTPC spacepoints, thus eliminating the need to identify and fit the particle tracks. PEAR shows strong performance in reconstructing vertical vertex positions from simulated data, that is superior to the standard approach for all metrics considered. Furthermore, the deep learning approach can reconstruct the vertical vertex position when the standard approach fails.

The ALPHA-g experiment at CERN aims to perform the first-ever direct measurement of the effect of gravity on antimatter, determining its weight to within 1% precision. This measurement requires an accurate prediction of the vertical position of annihilations within the detector. In this work, we present a novel approach to annihilation position reconstruction using an ensemble of models based on the PointNet deep learning architecture. The newly developed model, PointNet Ensemble for Annihilation Reconstruction (PEAR) outperforms the standard approach to annihilation position reconstruction, providing more than twice the resolution while maintaining a similarly low bias. This work may also offer insights for similar efforts applying deep learning to experiments that require high resolution and low bias.

Ptychography is an advanced computational imaging technique in X-ray and electron microscopy. It has been widely adopted across scientific research fields, including physics, chemistry, biology, and materials science, as well as in industrial applications such as semiconductor characterization. In practice, obtaining high-quality ptychographic images requires simultaneous optimization of numerous experimental and algorithmic parameters. Traditionally, parameter selection often relies on trial and error, leading to low-throughput workflows and potential human bias. In this work, we develop the "Ptychographic Experiment and Analysis Robot" (PEAR), a framework that leverages large language models (LLMs) to automate data analysis in ptychography. To ensure high robustness and accuracy, PEAR employs multiple LLM agents for tasks including knowledge retrieval, code generation, parameter recommendation, and image reasoning. Our study demonstrates that PEAR's multi-agent design significantly improves the workflow success rate, even with smaller open-weight models such as LLaMA 3.1 8B. PEAR also supports various automation levels and is designed to work with customized local knowledge bases, ensuring flexibility and adaptability across different research environments.

Large language models (LLMs) enhanced with retrieval-augmented generation (RAG) have introduced a new paradigm for web search. However, the limited context awareness of LLMs degrades their performance on RAG tasks. Existing methods to enhance context awareness are often inefficient, incurring time or memory overhead during inference, and many are tailored to specific position embeddings. In this paper, we propose Position-Embedding-Agnostic attention Re-weighting (PEAR), which enhances the context awareness of LLMs with zero inference overhead. Specifically, on a proxy task focused on context copying, we first detect heads which suppress the models' context awareness thereby diminishing RAG performance. To weaken the impact of these heads, we re-weight their outputs with learnable coefficients. The LLM (with frozen parameters) is optimized by adjusting these coefficients to minimize loss on the proxy task. As a result, the coefficients are optimized to values less than one, thereby reducing their tendency to suppress RAG performance. During inference, the optimized coefficients are fixed to re-weight these heads, regardless of the specific task at hand. Our proposed PEAR offers two major advantages over previous approaches: (1) It introduces zero additional inference overhead in terms of memory usage or inference time, while outperforming competitive baselines in accuracy and efficiency across various RAG tasks. (2) It is independent of position embedding algorithms, ensuring broader applicability.

Algorithmic Recourse (AR) is the problem of computing a sequence of actions that -- once performed by a user -- overturns an undesirable machine decision. It is paramount that the sequence of actions does not require too much effort for users to implement. Yet, most approaches to AR assume that actions cost the same for all users, and thus may recommend unfairly expensive recourse plans to certain users. Prompted by this observation, we introduce PEAR, the first human-in-the-loop approach capable of providing personalized algorithmic recourse tailored to the needs of any end-user. PEAR builds on insights from Bayesian Preference Elicitation to iteratively refine an estimate of the costs of actions by asking choice set queries to the target user. The queries themselves are computed by maximizing the Expected Utility of Selection, a principled measure of information gain accounting for uncertainty on both the cost estimate and the user's responses. PEAR integrates elicitation into a Reinforcement Learning agent coupled with Monte Carlo Tree Search to quickly identify promising recourse plans. Our empirical evaluation on real-world datasets highlights how PEAR produces high-quality personalized recourse in only a handful of iterations.

We present SPEAR, an open-source python library for data programming with semi supervision. The package implements several recent data programming approaches including facility to programmatically label and build training data. SPEAR facilitates weak supervision in the form of heuristics (or rules) and association of noisy labels to the training dataset. These noisy labels are aggregated to assign labels to the unlabeled data for downstream tasks. We have implemented several label aggregation approaches that aggregate the noisy labels and then train using the noisily labeled set in a cascaded manner. Our implementation also includes other approaches that jointly aggregate and train the model for text classification tasks. Thus, in our python package, we integrate several cascade and joint data-programming approaches while also providing the facility of data programming by letting the user define labeling functions or rules. The code and tutorial notebooks are available at https://github.com/decile-team/spear. Further, extensive documentation can be found at https://spear-decile.readthedocs.io/. Video tutorials demonstrating the usage of our package are available here. We also present some real-world use cases of SPEAR.

After months of rumors, Google announced its own smartwatch, called the Pixel Watch, will be coming this fall. Although the tech giant has supported smartwatches through its wearable operating system and completed its acquisition of Fitbit last year, this is Google's first branded smartwatch. The Pixel Watch will have a circular, domed design made with recycled stainless steel and customizable bands. Even though the watch also has plenty of features not concerned with health tracking, Rick Osterloh, Google's senior vice president of devices and services, teased the Pixel Watch's "deep integration" with Fitbit that will include heart rate and sleep tracking as well as workout metrics users can measure against their goals. Meanwhile, Google is entering a crowded market for health-tracking wearables, with competitors like Apple, Amazon, Samsung, Withings and Garmin.

Chiba – Researchers in Japan have been conducting experiments using robotics and artificial intelligence to alleviate fruit farmers' reliance on scarce labor while supporting those who are aging and have no successor. Trials are underway in Chiba Prefecture, a major production area for Japanese pears, and Yamanashi Prefecture, the country's main grape-growing region. In spring this year, a consortium made up of the Chiba Prefectural Government, agricultural cooperatives, and other concerns launched a two-year experimental project at pear-growing properties in the cities of Ichikawa and Narita in the prefecture. According to Tokyo-based consulting company NTT Data Institute of Management Consulting Inc., which oversees the experiments, a robot cargo vehicle automatically follows workers as they harvest pears, transporting the fruit to a designated location. An integrated camera shoots photographs of the prepicked pears and surrounding foliage, AI analyzes the data and provides information on the best time for the fruit to be harvested based on its growth.

Walk into any grocery store in America and you'll find a variety of fresh apples for consumption. It's remarkable to think how developed markets have managed to secure the availability of apples year-round. That miracle is made possible through lots of behind-the-scenes work that takes place at packing houses to ensure only the best fruit makes its way to grocery store produce sections. Take Washington State for example, where 58% of the apples grown in the United States are produced at a value of $2.5 billion yearly. Somewhere around 100 packing warehouses across the state work almost year-round to provide apples for domestic consumption with 30% of the product getting exported across the globe.