2/24/2026
Transitive RL: Value Learning via Divide and Conquer
RL algorithm using divide-and-conquer for offline goal-conditioned reinforcement learning value estimation.
2/24/2026
Bayesian Network Structure Discovery Using Large Language Models
Uses LLMs as core component for Bayesian network structure discovery from data, replacing traditional structure learning methods that require extensive observational data.
2/24/2026
Test-Time Adaptation for LLM Agents via Environment Interaction
Method for adapting LLM agents to novel environments through test-time interaction, addressing syntactic and semantic mismatches in observation formats and state dynamics.
2/24/2026
Leak@$k$: Unlearning Does Not Make LLMs Forget Under Probabilistic Decoding
Leak@k: study showing existing LLM unlearning methods fail under probabilistic decoding despite success under greedy decoding evaluation.
2/24/2026
Blind Inverse Game Theory: Jointly Decoding Rewards and Rationality in Entropy-Regularized Competitive Games
Blind-IGT: inverse game theory method jointly decoding rewards and rationality in entropy-regularized competitive games with unknown rationality parameter.
2/24/2026
Multistep Quasimetric Learning for Scalable Goal-conditioned Reinforcement Learning
Quasimetric learning method for goal-conditioned RL using multi-step returns to estimate temporal distance between observations over long horizons.
2/24/2026
FlowCast: Advancing Precipitation Nowcasting with Conditional Flow Matching
FlowCast: conditional flow matching method for radar-based precipitation nowcasting addressing uncertainty and high-dimensional data modeling.
2/24/2026
Scalable Multi-Objective and Meta Reinforcement Learning via Gradient Estimation
Gradient estimation method for multi-objective and meta reinforcement learning, partitioning n objectives into k groups for language model preference optimization.
2/24/2026
InTAct: Interval-based Task Activation Consolidation for Continual Learning
InTAct: continual learning approach using interval-based task activation consolidation with mathematical guarantees against catastrophic forgetting.
2/24/2026
MIST: Mutual Information Estimation Via Supervised Training
MIST: neural network-based mutual information estimator trained on 625K synthetic distributions with known ground-truth MI.
2/24/2026
E2E-GRec: An End-to-End Joint Training Framework for Graph Neural Networks and Recommender Systems
E2E-GRec framework for end-to-end joint training of GNNs and recommender systems, replacing two-stage pipeline approach.
2/24/2026
SelfAI: A self-directed framework for long-horizon scientific discovery
SelfAI multi-agent system for self-directed long-horizon scientific discovery with human-in-the-loop workflows and exploration trade-offs.
2/24/2026
ML-Tool-Bench: Tool-Augmented Planning for ML Tasks
ML-Tool-Bench framework for tool-augmented planning in autonomous ML agents orchestrating data analysis and model optimization workflows.
2/24/2026
Group Representational Position Encoding
GRAPE framework unifying positional encoding mechanisms using group actions for multiplicative rotations and additive biases.
2/24/2026
Can You Hear Me Now? A Benchmark for Long-Range Graph Propagation
ECHO benchmark for evaluating graph neural networks on long-range graph propagation and interaction tasks.
2/24/2026
Clust-PSI-PFL: A Population Stability Index Approach for Clustered Non-IID Personalized Federated Learning
Clustered personalized federated learning framework using Population Stability Index to handle non-IID data across clients.
2/24/2026
Divided We Fall: Defending Against Adversarial Attacks via Soft-Gated Fractional Mixture-of-Experts with Randomized Adversarial Training
Soft-gated fractional mixture-of-experts with randomized adversarial training to defend ML models against adversarial attacks.
2/24/2026
Precision Autotuning for Linear Solvers via Reinforcement Learning
RL framework for adaptive precision tuning in linear solvers using contextual bandit approach to balance precision and efficiency.
2/24/2026
HeurekaBench: A Benchmarking Framework for AI Co-scientist
HeurekaBench benchmarking framework for evaluating LLM-based AI co-scientist agents on end-to-end scientific analysis tasks.
2/24/2026
Self-Augmented Mixture-of-Experts for QoS Prediction
Mixture-of-experts model with self-augmentation for Quality of Service prediction in web service recommendation systems.
2/24/2026
Inverting Self-Organizing Maps: A Unified Activation-Based Framework
Method for inverting Self-Organizing Maps as generative models using activation patterns and distance geometry to reconstruct inputs.
2/24/2026
FaLW: A Forgetting-aware Loss Reweighting for Long-tailed Unlearning
Machine unlearning method addressing long-tailed distributions in forget sets using forgetting-aware loss reweighting for privacy compliance.
2/24/2026
Gradient-Aligned Calibration for Post-Training Quantization of Diffusion Models
Gradient-aligned calibration method for post-training quantization of diffusion models to accelerate inference and reduce memory usage.
2/24/2026
Improving the Trade-off Between Watermark Strength and Speculative Sampling Efficiency for Language Models
Research on trade-off between LLM watermarking strength and speculative sampling efficiency, proposing methods to improve both simultaneously.
2/24/2026
Recurrent Equivariant Constraint Modulation: Learning Per-Layer Symmetry Relaxation from Data
Method for learning per-layer equivariance relaxation in neural networks without manual hyperparameter tuning, improving optimization dynamics.
2/24/2026
TextME: Bridging Unseen Modalities Through Text Descriptions
TextME enables multimodal expansion using text-only training, projecting diverse modalities into LLM embeddings without paired datasets.
2/24/2026
EBPO: Empirical Bayes Shrinkage for Stabilizing Group-Relative Policy Optimization
EBPO addresses stability issues in Group Relative Policy Optimization for LLM reasoning via Empirical Bayes shrinkage, reducing variance and gradient problems.
2/24/2026
Causal Schr\"odinger Bridges: Constrained Optimal Transport on Structural Manifolds
arXiv paper on causal Schrödinger bridges for constrained optimal transport in generative modeling under causal interventions.
2/24/2026
Breaking the Simplification Bottleneck in Amortized Neural Symbolic Regression
arXiv paper on amortized neural symbolic regression addressing expression simplification bottleneck for discovering interpretable analytical expressions.
2/24/2026
Fast Catch-Up, Late Switching: Optimal Batch Size Scheduling via Functional Scaling Laws
arXiv paper analyzing optimal batch size scheduling for large-scale deep learning using functional scaling law framework.
2/24/2026
Conformal Signal Temporal Logic for Robust Reinforcement Learning Control: A Case Study
arXiv paper on formal temporal logic specifications enhancing safety of reinforcement learning control in aerospace F-16 simulation.
2/24/2026
HAWX: A Hardware-Aware FrameWork for Fast and Scalable ApproXimation of DNNs
arXiv paper on HAWX, hardware-aware framework for fast DNN approximation using multi-level sensitivity scoring and heterogeneous approximate computing.
2/24/2026
Optimizer choice matters for the emergence of Neural Collapse
arXiv paper analyzing role of optimizer choice in Neural Collapse emergence during deep neural network training terminal phase.
2/24/2026
Action-Graph Policies: Learning Action Co-dependencies in Multi-Agent Reinforcement Learning
arXiv paper proposing Action-Graph Policies for modeling action dependencies and coordination in multi-agent reinforcement learning systems.
2/24/2026
Powering Up Zeroth-Order Training via Subspace Gradient Orthogonalization
arXiv paper on zeroth-order optimization for fine-tuning large-scale models via subspace gradient orthogonalization, improving accuracy-efficiency tradeoff.
2/24/2026
Optimal Local Convergence Rates of Stochastic First-Order Methods under Local $\alpha$-PL
Research on local convergence rates of stochastic first-order methods under Polyak-Lojasiewicz conditions, a theoretical ML optimization problem.
2/24/2026
Against AI Enthusiasm and AI Fear: The Interface Problem
Essay examining the interface problem between AI capabilities and real-world impact, citing Sakana AI's autonomous research system achieving peer-review publication.
2/24/2026
Do Bubbles Form When AIs Simulate Capitalism?
Research paper demonstrating multiple AI agents connected to live trading APIs all bankrupted within 30 minutes due to LLM hallucination causing false market citations.
2/24/2026
Show HN: Indie AI Directory – A Curated List of Indie AI Tools
Curated directory of indie AI tools, startups, and APIs created by independent developers and solo founders with searchable categorization.
2/24/2026
ReasonDB – A database that reasons through your documents
AI-native document database built in Rust enabling AI agents to reason through documents via structural reasoning rather than vector similarity retrieval.
2/24/2026
Show HN: An AI voice agent that navigates IVR and negotiates retention discounts
AI voice agent that autonomously navigates IVR phone systems and negotiates customer retention discounts.
2/24/2026
Show HN: Thisorthis.ai – Compare responses from 50 AI models side-by-side
thisorthis.ai compares responses from 47+ text and image models side-by-side. Users submit one prompt and see outputs from ChatGPT, Claude, Gemini and others simultaneously with SmartPick LLM evaluation.
2/24/2026
Show HN: Anno – API that cuts AI web-scraping token costs by 90%
Anno API extracts clean structured text from web pages, reducing AI agent token consumption by 93% (600 vs 15,000 tokens per page). HTTP-based with ensemble extraction and confidence scoring.
2/24/2026
Show HN: System prompts and models of top AI tools (Claude Code, Cursor, Devin)
Repository of system prompts and internal models from Claude Code, Cursor, Devin, and other AI coding tools for reference.
2/24/2026
Show HN: Clawphone – Twilio voice/SMS gateway for AI agents using TwiML polling
Clawphone bridges Twilio voice/SMS to OpenClaw AI agents via TwiML polling without WebSocket servers or external STT/TTS APIs.
2/24/2026
Automatically Learning Skills for Coding Agents
gskill automates creation of skill files for coding agents from GitHub repositories, boosting resolve rates from 55% to 82% on Jinja and 24% to 93% on Bleve.
2/24/2026
Get to Know OpenClaw Security
Security guide for OpenClaw, a self-hosted AI agent gateway connecting LLMs to messaging platforms (Slack, Discord, Telegram) with tool access and local execution.
2/24/2026
We Reached 74.8% on terminal-bench with Terminus-KIRA
Terminus-KIRA AI agent achieved 74.8% on terminal-bench benchmark for evaluating agent performance on terminal-based engineering tasks like debugging and coding.
2/24/2026
Ask HN: How do you handle API rate limits in production?
Discussion thread asking about production strategies for handling API rate limiting across multiple workers, circuit breakers, and retry storms.
2/24/2026
Getting Real with LLMs
Critical analysis mapping real-world engineering tasks to LLM/agent tool capabilities, distinguishing genuine functionality from hype in ecosystem claims.