FORT synthesizes shortcut-resistant search tasks by controlling four identified shortcut risks across entity selection, graph construction, question formulation, and refinement, producing training data that yields agents with longer search trajectories and top performance among open-source models on
hub
arXiv preprint arXiv:2508.02085 , year=
27 Pith papers cite this work. Polarity classification is still indexing.
27
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
verdicts
UNVERDICTED 27roles
background 4representative citing papers
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.
CyberEvolver introduces a four-layer self-evolving agent architecture with trace-to-diagnosis and population beam search that raises seed agent success rates by 13.6% on CTF, exploitation, and penetration tasks across four LLMs.
EXG is an experience graph framework for self-evolving LLM agents that supports online real-time growth and offline reuse to enhance solution quality and efficiency on code generation and reasoning benchmarks.
SaaSBench introduces a heterogeneous benchmark for enterprise SaaS engineering and shows that state-of-the-art coding agents fail over 95% of the time before reaching deep business logic due to setup and integration problems.
ConeSep tackles noisy triplet correspondences in composed image retrieval by introducing geometric fidelity quantization to locate noise, negative boundary learning for semantic opposites, and targeted unlearning via optimal transport, outperforming prior methods on FashionIQ and CIRR.
IFCodeEvolve synthesizes coding data via actor-schema co-evolution with MCTS, boosting a 32B model's performance to match proprietary SOTA on instruction following.
EpiEvolve achieves 0.629 accuracy in streaming COVID-19 forecasting by using episodic memory, reflection on delayed labels, and regime-aware retrieval, outperforming static LLMs (0.561) and CDC ensembles (0.325) while halving recovery lag after regime shifts.
Meta-Team is a collaborative self-evolution framework that turns multi-agent execution experience into reusable improvements at agent, coordination, and team levels, outperforming baselines on six benchmarks.
SEAL co-evolves LLM agents and environments via shared turn-level failure diagnoses, yielding +8.25 to +26.25 point gains on tool-use tasks with only 400 samples.
PACE coordinates low-risk prompt evolution with validated higher-risk control-logic updates to improve frozen SLM agents on benchmarks without model retraining.
PIVOT refines LLM agent trajectories through plan-inspect-evolve-verify stages using environment feedback, yielding up to 94% relative gains in constraint satisfaction and 3-5x token efficiency over prior refinement methods.
CoRM-RAG uses a cognitive perturbation protocol to simulate biases and trains an Evidence Critic to retrieve documents that support correct decisions even under adversarial query changes.
Air-Know decouples MLLM-based external arbitration from proxy learning via knowledge internalization and dual-stream training to overcome noisy triplet correspondence in composed image retrieval.
HEAL mitigates entropy collapse in few-shot RLVR by selectively adding general-domain data and aligning trajectory-level entropy dynamics, matching full-shot performance with 32 target samples.
AgentGA optimizes agent seeds with genetic algorithms and parent-archive inheritance to improve autonomous code generation, beating a baseline on 15 of 16 Kaggle competitions.
MachineLearningLM uses continued pretraining on SCM-synthesized ML tasks with random-forest distillation to give LLMs robust many-shot in-context learning on tabular classification, reaching random-forest accuracy levels while preserving general chat performance.
ParametricSkills uses a hypernetwork to turn textual skills into LoRA adapters, outperforming in-context learning by 6.44 points on average across six SWE subtasks with higher BERT Score and F1.
SkillDisCo distills reusable PFSM subgraphs from successful agent traces and compiles them into callable procedural skills, improving success rates and reducing turns on ALFWorld and WebArena.
MAA formalizes alignability and comparability conditions and uses differential signals, EMA accumulation, and semantic identity merging to enable cross-batch operation-level evidence accumulation, outperforming batch-level baselines in 14 of 16 settings while matching online methods.
ReQueR trains a single RL-based query refiner with an adaptive curriculum to decompose raw queries into structured logic, delivering 1.7-7.2% absolute gains on reasoning tasks across diverse LLMs and generalizing to unseen models.
SEARL uses a tool graph memory that integrates planning and execution to densify rewards and improve generalization in self-evolving agents on knowledge and math tasks.
STITCH trains superior agentic coding and reasoning LLMs by using fewer high-quality trajectories filtered to keep only critical decision tokens, delivering up to 63% relative gains on SWE-bench Verified.
RankVR introduces GSCP and ASVC modules to improve CIR robustness by decoupling clean samples via low-rank structure and dynamically scoring triplet value in noisy datasets.
citing papers explorer
-
FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents
FORT synthesizes shortcut-resistant search tasks by controlling four identified shortcut risks across entity selection, graph construction, question formulation, and refinement, producing training data that yields agents with longer search trajectories and top performance among open-source models on
-
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.
-
CyberEvolver: Structured Self-Evolution for Cybersecurity Agents On the Fly
CyberEvolver introduces a four-layer self-evolving agent architecture with trace-to-diagnosis and population beam search that raises seed agent success rates by 13.6% on CTF, exploitation, and penetration tasks across four LLMs.
-
EXG: Self-Evolving Agents with Experience Graphs
EXG is an experience graph framework for self-evolving LLM agents that supports online real-time growth and offline reuse to enhance solution quality and efficiency on code generation and reasoning benchmarks.
-
SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering
SaaSBench introduces a heterogeneous benchmark for enterprise SaaS engineering and shows that state-of-the-art coding agents fail over 95% of the time before reaching deep business logic due to setup and integration problems.
-
ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval
ConeSep tackles noisy triplet correspondences in composed image retrieval by introducing geometric fidelity quantization to locate noise, negative boundary learning for semantic opposites, and targeted unlearning via optimal transport, outperforming prior methods on FashionIQ and CIRR.
-
Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution
IFCodeEvolve synthesizes coding data via actor-schema co-evolution with MCTS, boosting a 32B model's performance to match proprietary SOTA on instruction following.
-
EpiEvolve: Self-Evolving Agents for Streaming Pandemic Forecasting under Regime Shifts
EpiEvolve achieves 0.629 accuracy in streaming COVID-19 forecasting by using episodic memory, reflection on delayed labels, and regime-aware retrieval, outperforming static LLMs (0.561) and CDC ensembles (0.325) while halving recovery lag after regime shifts.
-
Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems
Meta-Team is a collaborative self-evolution framework that turns multi-agent execution experience into reusable improvements at agent, coordination, and team levels, outperforming baselines on six benchmarks.
-
SEAL: Synergistic Co-Evolution of Agents and Learning Environments
SEAL co-evolves LLM agents and environments via shared turn-level failure diagnoses, yielding +8.25 to +26.25 point gains on tool-use tasks with only 400 samples.
-
PACE: Two-Timescale Self-Evolution for Small Language Model Agents
PACE coordinates low-risk prompt evolution with validated higher-risk control-logic updates to improve frozen SLM agents on benchmarks without model retraining.
-
PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement
PIVOT refines LLM agent trajectories through plan-inspect-evolve-verify stages using environment feedback, yielding up to 94% relative gains in constraint satisfaction and 3-5x token efficiency over prior refinement methods.
-
Beyond Semantic Relevance: Counterfactual Risk Minimization for Robust Retrieval-Augmented Generation
CoRM-RAG uses a cognitive perturbation protocol to simulate biases and trains an Evidence Critic to retrieve documents that support correct decisions even under adversarial query changes.
-
Air-Know: Arbiter-Calibrated Knowledge-Internalizing Robust Network for Composed Image Retrieval
Air-Know decouples MLLM-based external arbitration from proxy learning via knowledge internalization and dual-stream training to overcome noisy triplet correspondence in composed image retrieval.
-
HEALing Entropy Collapse: Enhancing Exploration in Few-Shot RLVR via Hybrid-Domain Entropy Dynamics Alignment
HEAL mitigates entropy collapse in few-shot RLVR by selectively adding general-domain data and aligning trajectory-level entropy dynamics, matching full-shot performance with 32 target samples.
-
AgentGA: Evolving Code Solutions in Agent-Seed Space
AgentGA optimizes agent seeds with genetic algorithms and parent-archive inheritance to improve autonomous code generation, beating a baseline on 15 of 16 Kaggle competitions.
-
MachineLearningLM: Scaling Many-shot In-context Learning via Continued Pretraining
MachineLearningLM uses continued pretraining on SCM-synthesized ML tasks with random-forest distillation to give LLMs robust many-shot in-context learning on tabular classification, reaching random-forest accuracy levels while preserving general chat performance.
-
Parametric Skills
ParametricSkills uses a hypernetwork to turn textual skills into LoRA adapters, outperforming in-context learning by 6.44 points on average across six SWE subtasks with higher BERT Score and F1.
-
SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills
SkillDisCo distills reusable PFSM subgraphs from successful agent traces and compiles them into callable procedural skills, improving success rates and reducing turns on ALFWorld and WebArena.
-
Marginal Advantage Accumulation for Memory-Driven Agent Self-Evolution
MAA formalizes alignability and comparability conditions and uses differential signals, EMA accumulation, and semantic identity merging to enable cross-batch operation-level evidence accumulation, outperforming batch-level baselines in 14 of 16 settings while matching online methods.
-
One Refiner to Unlock Them All: Inference-Time Reasoning Elicitation via Reinforcement Query Refinement
ReQueR trains a single RL-based query refiner with an adaptive curriculum to decompose raw queries into structured logic, delivering 1.7-7.2% absolute gains on reasoning tasks across diverse LLMs and generalizing to unseen models.
-
SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents
SEARL uses a tool graph memory that integrates planning and execution to densify rewards and improve generalization in self-evolving agents on knowledge and math tasks.
-
Yet Even Less Is Even Better For Agentic, Reasoning, and Coding LLMs
STITCH trains superior agentic coding and reasoning LLMs by using fewer high-quality trajectories filtered to keep only critical decision tokens, delivering up to 63% relative gains on SWE-bench Verified.
-
RankVR: Low-Rank Structure Perception and Value Recalibration for Robust Composed Image Retrieval
RankVR introduces GSCP and ASVC modules to improve CIR robustness by decoupling clean samples via low-rank structure and dynamically scoring triplet value in noisy datasets.
-
IMAGINE: Adaptive Schema-Imagery Enhanced Composition for Composed Video Retrieval
IMAGINE uses adaptive schema-imagery via dynamic multimodal prototypes to incorporate implicit semantics into composed video retrieval, claiming SOTA results on CVR and CIR benchmarks.
-
ANCHOR: Abductive Network Construction with Hierarchical Orchestration for Reliable Probability Inference in Large Language Models
ANCHOR uses hierarchical factor construction and causal Bayesian networks to reduce unknown predictions and improve reliability of LLM-based probability inference over prior Naive Bayes approaches.
-
OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction
OxyGent supplies a modular framework for multi-agent systems via the Oxy abstraction for composition and monitoring and the OxyBank engine for continuous automated evolution.