3 papers
cs.AI2026
ToolSelf: Unifying Task Execution and Self-Reconfiguration via Tool-Driven Emergent Adaptation
Jingqi Zhou, Sheng Wang, Dezhao Deng +9
LLM-powered agentic systems excel at complex long-horizon tasks, but remain constrained by static configurations fixed before execution. Such rigidity forces a trade-off between do…
cs.AI2026
LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition
Yanyu Chen, Jiyue Jiang, Dianzhi Yu +8
The evolution of Large Language Model (LLM) reasoning is bottlenecked by the scarcity of high-quality process data. While self-alignment via endogenous rewards offers a solution, m…
cs.CL2026
TRACE: Trajectory-Aware Comprehensive Evaluation for Deep Research Agents
Yanyu Chen, Jiyue Jiang, Jiahong Liu +3
The evaluation of Deep Research Agents is a critical challenge, as conventional outcome-based metrics fail to capture the nuances of their complex reasoning. Current evaluation fac…