RISE uses BM25 to bound interaction spaces for agentic search and pre-processes documents for shell navigation, matching direct corpus interaction accuracy at roughly one-quarter the cost on BrowseComp-Plus.
Coding agents are effective long-context processors
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
SkillHarm benchmark shows current AI agents are vulnerable to lifecycle-aware skill poisoning with success rates up to 86.3% for fixed-payload attacks and 69.3% for self-mutating attacks.
LongMemEval-V2 is a new benchmark where AgentRunbook-C reaches 72.5% accuracy on long-term agent memory tasks, beating RAG baselines at 48.5% and basic coding agents at 69.3%.
SkillFlow benchmark shows lifelong skill evolution yields modest gains for some models like Claude Opus 4.6 but limited or negative utility for others despite high skill usage.
RAH improves coding performance on Oolong-Synthetic from 71.75% to 81.36% with fixed GPT-5 backbone by spawning subagent harnesses via executable scripts.
citing papers explorer
-
Towards Retrieving Interaction Spaces for Agentic Search
RISE uses BM25 to bound interaction spaces for agentic search and pre-processes documents for shell navigation, matching direct corpus interaction accuracy at roughly one-quarter the cost on BrowseComp-Plus.
-
SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction
SkillHarm benchmark shows current AI agents are vulnerable to lifecycle-aware skill poisoning with success rates up to 86.3% for fixed-payload attacks and 69.3% for self-mutating attacks.
-
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
LongMemEval-V2 is a new benchmark where AgentRunbook-C reaches 72.5% accuracy on long-term agent memory tasks, beating RAG baselines at 48.5% and basic coding agents at 69.3%.
-
SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents
SkillFlow benchmark shows lifelong skill evolution yields modest gains for some models like Claude Opus 4.6 but limited or negative utility for others despite high skill usage.
-
Recursive Agent Harnesses
RAH improves coding performance on Oolong-Synthetic from 71.75% to 81.36% with fixed GPT-5 backbone by spawning subagent harnesses via executable scripts.