norgitov/ trends
Technology · people · ideas
RSS
RUEN
Back to discovery/Daily Papers1 hour ago
ResearchDaily Papers

Groupwise Agentic Grading and Advantage Redistribution for Code Agent RL

The paper introduces GAGAR, a framework for quality-aware credit redistribution in code agent reinforcement learning (RL). It uses dynamic sampling and an SFT-trained agentic grader to rank test-passing trajectories, adjusting advantages to prioritize higher-quality implementations. The method was evaluated on large-scale industrial code agents with significant parameter counts.

Open original
SIGNAL FROM THE SOURCE
26
source votes
Tracking sinceSeptember 29, 202626 source votes
Momentum+8.29/hover 3.02 h
Discussion—Read comments ↗
PublishedSeptember 26, 2026Jinhao Dong, Liang Zhao, Zihao Yue
BEHIND THE NUMBERS

How interest changes

Daily Papers

History starts here

The chart will appear after repeat observations. The current metric comes from the source.

26 source votes

Real observations only. History before source connection is not reconstructed.

WHY IT MAY MATTER

This approach improves code agent training by prioritizing high-quality implementations through dynamic credit redistribution, which may lead to more stable and effective learning in software development tasks.

A useful discovery?
KEEP EXPLORING

Connected ideas

Explore topic
Daily Papers

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

The paper explores the linearity in Large Language Models (LLMs) by showing that combining inputs from different text streams leads to a superposition of next-token distributions. It suggests that this linearity is an inherent property of the Transformer architecture and can be restored through fine-tuning, allowing for generating two coherent continuations from one forward pass.

5 days agoDaily Papers

FuseReg: Regularizing Layer Fusion Mitigates the Reconstruction-Generation Gap in Representation Autoencoders

This paper introduces FuseReg, a method that replaces heuristic layer fusion in representation autoencoders (RAEs) with training over random subsets of encoder layers. The approach reduces the reconstruction-generation gap by improving robustness to layer fusion choices, achieving higher PSNR and lower generation FID scores without modifying the pretrained encoder.

4 days agoDaily Papers

Learning to Learn from Context: Synthetic Training from Perturbed Public Documents

This paper introduces a method to enhance large language models' (LLMs) ability to learn from context by using perturbed public documents. The approach involves rewriting documents, generating reasoning-based questions, and training a student model on these synthetic samples, leading to improved performance on CL-bench and broader transfer to tasks like long-context understanding and reasoning.

2 days agoDaily Papers

Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents

The paper introduces Skill2Env, a framework that generates executable environments from skills by using agent capability demands to create task blueprints with objectives, challenges, and evaluation criteria. It also proposes Iterative Task Hardening to improve task difficulty based on solver execution evidence, leading to improved agent performance across benchmarks.

2 days agoDaily Papers

Block Sparse Attention with Log-Linear Complexity

The paper introduces PISA, a block-sparse attention mechanism with log-linear complexity, designed to scale language models for long contexts. It uses a pyramid Top-K selection strategy to efficiently identify relevant keys, reducing computational cost compared to traditional methods.

4 days agoDaily Papers

The Past Frames the Future: Memory for Autoregressive Video Generation

This paper reviews memory mechanisms in autoregressive (AR) video generation, focusing on how historical information influences future generations despite limited context windows. It organizes the literature through five perspectives: forms, functions, operations, learning, and evaluation, highlighting challenges like resource-aware memory architectures and standardized evaluation.

6 days ago