Reversa is a reverse documentation engineering framework that deploys a multi-agent pipeline to extract implicit rules from legacy software and produce traceable specifications with confidence scores and explicit gaps for human review.
Learning from failure: Integrating negative examples when fine-tuning large language models as agents
5 Pith papers cite this work, alongside 2 external citations. Polarity classification is still indexing.
5
Pith papers citing it
2
external citations · external index
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Open-weight LLMs exhibit tool suppression under joint tool-calling and JSON-schema constraints due to grammar token masking; a two-pass inference method restores tool use.
FATE lets LLM agents self-evolve safer behaviors by generating and filtering repairs from their own failure trajectories using verifiers and Pareto optimization.
SpanVLA reduces action generation latency via flow-matching conditioned on history and improves robustness by training on negative-recovery samples with GRPO and a dedicated reasoning dataset.
AdaSwitch improves small local LLM performance on reasoning tasks by adaptively switching to a large cloud LLM upon detected errors, sometimes matching cloud results with far less overhead.
citing papers explorer
-
Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents
Reversa is a reverse documentation engineering framework that deploys a multi-agent pipeline to extract implicit rules from legacy software and produce traceable specifications with confidence scores and explicit gaps for human review.
-
Constraint Tax in Open-Weight LLMs: An Empirical Study of Tool Calling Suppression Under Structured Output Constraints
Open-weight LLMs exhibit tool suppression under joint tool-calling and JSON-schema constraints due to grammar token masking; a two-pass inference method restores tool use.
-
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment
FATE lets LLM agents self-evolve safer behaviors by generating and filtering repairs from their own failure trajectories using verifiers and Pareto optimization.
-
SpanVLA: Efficient Action Bridging and Learning from Negative-Recovery Samples for Vision-Language-Action Model
SpanVLA reduces action generation latency via flow-matching conditioned on history and improves robustness by training on negative-recovery samples with GRPO and a dedicated reasoning dataset.
-
AdaSwitch: Adaptive Switching between Small and Large Agents for Effective Cloud-Local Collaborative Learning
AdaSwitch improves small local LLM performance on reasoning tasks by adaptively switching to a large cloud LLM upon detected errors, sometimes matching cloud results with far less overhead.