# ReAct loop

The authors introduce a measurement protocol that traces, from the scripts and notes a coding agent writes alone, how knowledge is kept, rewritten or discarded at ARC-AGI-3 level boundaries; across seven runs with three backbones from two model families, scripts are almost never called again in a later task (33 of 630 references cross a boundary), 74% of pre-boundary scripts are abandoned, notes only grow, and the costliest error is a hard-coded value carried into a new task, whose one working repair is to turn the constant into a parameter supplied afresh per task.

The authors introduce a measurement protocol that traces, from the scripts and notes a coding agent writes alone, how knowledge is kept, rewritten or discarded at ARC-AGI-3 level boundaries; across seven runs with three backbones from two model families, scripts are almost never called again in a later task (33 of 630 references cross a boundary), 74% of pre-boundary scripts are abandoned, notes only grow, and the costliest error is a hard-coded value carried into a new task, whose one working repair is to turn the constant into a parameter supplied afresh per task.

The work introduces CogMem, a training-free cognitive memory architecture built on the PEC2F (Person-Event-Concept-Claim-Fact) graph schema: dedicated Claim nodes preserve the source and target of subjective statements, dialogue turns are incrementally converted into provenance-aware graph records and consolidated into higher-level facts, and a rule-based controller driven by LLM intent parsing composes four deterministic graph operators—anchoring, traversal, intersection, and evidence grounding—to reconstruct query-relevant context; on LoCoMo and LongMemEval it performs strongly on multi-hop, temporal, and knowledge-update tasks, with ablations and a semantic-collapse probe supporting complementary contributions from epistemic separation, consolidation, and agentic retrieval.

The work introduces CogMem, a training-free cognitive memory architecture built on the PEC2F (Person-Event-Concept-Claim-Fact) graph schema: dedicated Claim nodes preserve the source and target of subjective statements, dialogue turns are incrementally converted into provenance-aware graph records and consolidated into higher-level facts, and a rule-based controller driven by LLM intent parsing composes four deterministic graph operators—anchoring, traversal, intersection, and evidence grounding—to reconstruct query-relevant context; on LoCoMo and LongMemEval it performs strongly on multi-hop, temporal, and knowledge-update tasks, with ablations and a semantic-collapse probe supporting complementary contributions from epistemic separation, consolidation, and agentic retrieval.

The work presents ProsaBuddy, an LLM-based agent system that uses a ReAct loop with retrieval over the Prosa codebase, access to Rocq tools and optional human-written hints, and a subgoal-delegation architecture that decomposes a lemma into subgoals dispatched to subagents for proof, and on a mini benchmark drawn from real-time scheduling literature it significantly outperforms state-of-the-art LLM-based Rocq automated proving agent systems and the general coding agent OpenCode.

The work presents ProsaBuddy, an LLM-based agent system that uses a ReAct loop with retrieval over the Prosa codebase, access to Rocq tools and optional human-written hints, and a subgoal-delegation architecture that decomposes a lemma into subgoals dispatched to subagents for proof, and on a mini benchmark drawn from real-time scheduling literature it significantly outperforms state-of-the-art LLM-based Rocq automated proving agent systems and the general coding agent OpenCode.