new

Get trending papers in your email inbox once a day!

Get trending papers in your email inbox!

Daily Papers

byAK and the research community

Nov 12

Submitted by

Youqing

Scaling Mathematical Proof Supervision from Structured Textbooks

internlm

Intern Large Models

Submitted by

XXXXyu

SteerDistill: Quantizing LLM Agents via Closed-Loop Teacher Steering

·
6 authors

Submitted by

debouter

Incentivizing Self-Learning in Large Language Models via Reinforcement Learning

internlm

Intern Large Models

7

Submitted by

CapitalLiu

Read Less, Solve More: Token-Efficient Sparse Reading of External Content for AI Agents

ict-cas

Institute of Computing Technology

Submitted by

SaulUrso

Ensemble Routing for Prompt-Adaptive Cost-Aware LLM Inference

·
4 authors

1

Submitted by

ljbro

GTAGym: Real AAA Game Tasks Environment for Evaluation and Reinforcement Learning

OpenMOSS-Team

Submitted by

HaoKang

Evolving Infra: Agent-Adaptive LLM Serving at Scale

mit-han-lab

Submitted by

qbouniot

Where Does Alignment Emerge and What Does It Mean? A Closer Look at the Platonic Representation Hypothesis

TUM

Technical University of Munich

Submitted by

mnknayeem

Precision on Demand: Escalating Weight Bits at Uncertain Decoding Steps in a Small Local Model

·
3 authors

Submitted by

michaelzch001

Interactive Visual Gym: Evaluating Visual Interaction Models with Simulated Users in Interactive Worlds

·
14 authors

Submitted by

DaraV

Mixed Signals: Weight-Space Programming for EEG and ECG

epfl-ch

1

Submitted by

guyhadad01

Module-Aware Optimization for Graph Neural Networks

·
4 authors

Submitted by

dengzhe-hou

CogBattery: Human-Referenced Evaluation of Cognitive Task Behavior and Structure in Language Models

·
4 authors

Submitted by

dengzhe-hou

WMIP: A Working-Memory-Inspired Programmable Probe of Cumulative State Tracking in Large Language Models

·
6 authors

Submitted by

smrajkumar

FAME-QP: A GPU-Accelerated Quadratic-Programming Solver for Real-Time Model Predictive Control

ohiostate

The Ohio State University

Submitted by

dayll

CARTBench: Rubric-Based Evaluation of Shopping Advice for Complex and Ambiguous Requests with Timelines

·
12 authors

Submitted by

mnknayeem

Bits or permutations? Spending a fixed inference budget on weight precision or on option-order averaging in small local language models

·
3 authors

Submitted by

mnknayeem

PolyRoute: A Twelve-Language and Code-Mixed Benchmark for Typed-Decision Routing, with Baselines and a Leaderboard

·
2 authors

Submitted by

josephimperial

ScrapeBench: Evaluating Legal Compliance of AI Agents in Website Scraping

·
3 authors