Dockerless uses agentic repository exploration to verify patches without execution, enabling SFT and RL training of coding agents that reach 62.0/50.0/35.2% resolve rates on SWE-bench Verified/Multilingual/Pro while matching environment-based results.
hub
Air-bench: Automated heterogeneous information retrieval benchmark
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
SWE-Explore is a new benchmark evaluating repository exploration by coding agents on 848 issues across 203 repositories, using line-level ground truth from successful agent trajectories and showing agentic methods outperform classical retrieval on coverage and ranking.
EvoRepair is the first experience-based self-evolving agent framework for automated vulnerability repair, reporting 90.46% overall success on PATCHEVAL and SEC-bench benchmarks.
Multimodal LLMs process code as images to achieve up to 8x token compression, with visual cues like syntax highlighting aiding tasks and clone detection remaining resilient or even improving under compression.
InlineCoder reframes repository-level code generation as function-level coding by using a draft anchor to inline the target function into its call graph for upstream usage and downstream dependency context.
SWE-QA creates a new repository-level code QA benchmark with 576 pairs and an agentic LLM framework, showing promise but open challenges for models handling complex codebases.
Adding visual dependency-graph images to a text-based coding agent cuts token consumption by up to 26% while keeping issue-resolution accuracy roughly unchanged.
Three code-specific uncertainty axes (lexical, algorithmic, functional) yield an ensemble that raises average AUROC from 0.696 to 0.776 across five code LLMs, with one single-pass signal matching multi-pass baselines at lower cost.
SeqMem-Eval reveals that high final accuracy in sequential LLM memory tasks often coexists with substantial forgetting and negative transfer, exposing stability-adaptability trade-offs hidden by standard aggregate metrics.
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.
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.
Embedding dynamic analysis into an LLM repair agent yields a claimed 79.4% resolution rate on SWE-bench Verified while cutting token use by about 25%.
LMEB is a new benchmark that evaluates embedding models on long-horizon memory retrieval and shows this skill is largely orthogonal to traditional passage-retrieval performance.
Janus is a method-agnostic plug-in that uses a Memory Momentum Trigger and compact hybrid evaluation to selectively accept LLM memory updates, yielding +2.7 to +4.6 accuracy gains over base updaters on six datasets.
LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.
citing papers explorer
-
Dockerless: Environment-Free Program Verifier for Coding Agents
Dockerless uses agentic repository exploration to verify patches without execution, enabling SFT and RL training of coding agents that reach 62.0/50.0/35.2% resolve rates on SWE-bench Verified/Multilingual/Pro while matching environment-based results.
-
SWE-Explore: Benchmarking How Coding Agents Explore Repositories
SWE-Explore is a new benchmark evaluating repository exploration by coding agents on 848 issues across 203 repositories, using line-level ground truth from successful agent trajectories and showing agentic methods outperform classical retrieval on coverage and ranking.
-
EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolution
EvoRepair is the first experience-based self-evolving agent framework for automated vulnerability repair, reporting 90.46% overall success on PATCHEVAL and SEC-bench benchmarks.
-
CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding
Multimodal LLMs process code as images to achieve up to 8x token compression, with visual cues like syntax highlighting aiding tasks and clone detection remaining resilient or even improving under compression.
-
In Line with Context: Repository-Level Code Generation via Context Inlining
InlineCoder reframes repository-level code generation as function-level coding by using a draft anchor to inline the target function into its call graph for upstream usage and downstream dependency context.
-
SWE-QA: Can Language Models Answer Repository-level Code Questions?
SWE-QA creates a new repository-level code QA benchmark with 576 pairs and an agentic LLM framework, showing promise but open challenges for models handling complex codebases.
-
LLM Agents Can See Code Repositories
Adding visual dependency-graph images to a text-based coding agent cuts token consumption by up to 26% while keeping issue-resolution accuracy roughly unchanged.
-
Code Is More Than Text: Uncertainty Estimation for Code Generation
Three code-specific uncertainty axes (lexical, algorithmic, functional) yield an ensemble that raises average AUROC from 0.696 to 0.776 across five code LLMs, with one single-pass signal matching multi-pass baselines at lower cost.
-
Is One Score Enough? Rethinking the Evaluation of Sequentially Evolving LLM Memory
SeqMem-Eval reveals that high final accuracy in sequential LLM memory tasks often coexists with substantial forgetting and negative transfer, exposing stability-adaptability trade-offs hidden by standard aggregate metrics.
-
Step Rejection Fine-Tuning: A Practical Distillation Recipe
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.
-
Beyond Fixed Tests: Repository-Level Issue Resolution as Coevolution of Code and Behavioral Constraints
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.
-
Dynamic analysis enhances issue resolution
Embedding dynamic analysis into an LLM repair agent yields a claimed 79.4% resolution rate on SWE-bench Verified while cutting token use by about 25%.
-
LMEB: Long-horizon Memory Embedding Benchmark
LMEB is a new benchmark that evaluates embedding models on long-horizon memory retrieval and shows this skill is largely orthogonal to traditional passage-retrieval performance.
-
The Past Is Prologue: A Plug-in Controller for Selective Updates in Sequentially Evolving LLM Memory
Janus is a method-agnostic plug-in that uses a Memory Momentum Trigger and compact hybrid evaluation to selectively accept LLM memory updates, yielding +2.7 to +4.6 accuracy gains over base updaters on six datasets.
-
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
LLM agent progress depends on externalizing cognitive functions into memory, skills, protocols, and harness engineering that coordinates them reliably.
- ContextSniper: AntTrail's Token-Efficient Code Memory for Repository-Level Program Repair