DAIRA integrates dynamic tracing into LLM agents to achieve 79.4% resolution rate on SWE-bench Verified for code defect repair.
hub Canonical reference
Swe-search: Enhancing software agents with monte carlo tree search and iterative refinement
Canonical reference. 80% of citing Pith papers cite this work as background.
12
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 4
baseline 1
citation-polarity summary
representative citing papers
STRIDE co-trains generator and verifier on outcome rewards alone to deliver learnable stepwise language feedback that redirects LLM reasoning trajectories and outperforms scalar-reward baselines.
Step Rejection Fine-Tuning masks loss on erroneous steps identified by a critic LLM in unresolved trajectories, raising SWE-bench Verified resolution rate by 3.7% to 32.2% versus 2.4% for trajectory-level rejection.
GALA uses hierarchical graph alignment between UI screenshots and code structures to achieve state-of-the-art bug localization in multimodal automated program repair on SWE-bench.
More fault localization context does not consistently improve LLM-based program repair; file-level context gives 15-17x gains, optimal around 6-10 files, while line-level context often degrades performance from noise.
Agent-CoEvo is a multi-agent LLM framework that coevolves code patches and test patches to resolve repository-level issues, outperforming fixed-test baselines on SWE-bench Lite and SWT-bench Lite.
Evo-Memory is a new streaming benchmark and evaluation framework for self-evolving memory in LLM agents, unifying over ten memory modules and introducing the ReMem pipeline for continual improvement on multi-turn and reasoning datasets.
A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed open challenges.
LLM judges for code tasks show high sensitivity to prompt biases that systematically favor certain options, changing accuracy and model rankings even when code is unchanged.
The survey structures agentic reasoning for LLMs into foundational, self-evolving, and collective multi-agent layers while distinguishing in-context orchestration from post-training optimization and reviewing applications across domains.