- Rating
- 2(−1)
- Confidence
- 1
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
LLM agents lose track of important details over long conversations — context windows fill up, summaries drift, and external logic solvers are slow and brittle. This paper proposes "Think Ontologically," which trains the model to emit a small structured scratchpad of ontological predicates (like causes, holds_value, has_state, has_goal) before each response, instead of relying on prose memory or external solvers. The model is trained in two stages: 1) supervised warmup, then 2) RL with rule-based rewards. It is tested across five model families on IFEval, GPQA Diamond, and τ-bench, showing gains over baselines.
Critical strengths
Replacing external symbolic solvers with internalized ontological predicates trained via RL is a practical middle ground between pure prose memory and rigid neuro-symbolic pipelines. The framing through the "Conversational Memory Trilemma" makes the contribution easy to understand, and the latency reduction (>75%) over external solver pipelines is a real practical benefit.
Critical weaknesses
The paper's central motivation is about multi-turn conversational memory degradation, but two of the three benchmarks (IFEval and GPQA Diamond) are single-turn tasks. The only multi-turn benchmark (τ-bench) uses just 50 episodes with very wide confidence intervals. This makes it hard to be confident that the approach actually solves the memory problem it sets out to address.
All models are 14B parameters or smaller, and the training data is only 1,500 episodes. It's unclear whether the approach scales or whether the gains hold on larger models where baseline performance is already stronger.
Questions for authors
Have you evaluated on longer dialogue trajectories (e.g., 15–20+ turns)? The τ-bench tasks seem to cap around 5–10 turns, which may not stress-test the memory preservation claim enough.
We thank Reviewer UPLJ for the positive rating (Score: 3) and for highlighting the practical value of the Conversational Memory Trilemma framing and the >75% latency reduction over decoupled neuro-symbolic pipelines. Below we address both weaknesses raised in the review.
1. Multi-Turn Evaluation on τ-bench Airline (N=50, 250 Trajectories) & Cross-Domain Evaluation Design
Evaluation Scale on τ-bench Airline: The 50 airline scenarios in τ-bench Airline follow the standard benchmark specification established by Yao et al. (2024). To provide statistical rigor, our evaluation evaluates each of the 50 tasks across 5 retry seeds (yielding 250 full multi-turn conversational trajectories). In Table 3, our fine-tuned Qwen-2.5-14B achieves 88.0% ± 9.01% goal completion and 84.0% ± 10.17% constraint preservation, outperforming the zero-shot baseline (68.0% ± 12.92%) and Mem0 (70.0% ± 12.72%).
Complementary Cross-Domain Verification (IFEval and GPQA): Evaluating our checkpoints on IFEval (541 prompts, 841 verifiable rules) and GPQA Diamond (198 expert scientific questions) was a deliberate design choice:
2. Scaling Beyond 14B Parameters and 1,500 Training Episodes
Scaling to Frontier Models: As reported in Table R3 (Global Author Response), we evaluated our ontological scratchpad specification on 7 frontier models across 448 GPQA questions and on τ-bench Airline:
GPT-5.4from 70.31% to 74.55% (+4.24 pp),OpenAI o3from 44.87% to 52.46% (+7.59 pp), andGLM-5from 63.17% to 65.85% (+2.68 pp).GPT-5.4-nanogains +6.25 pp (51.56% to 57.81%).Why 1,500 Episodes Suffice for RLVR Internalization: Because our ontology uses a compact, closed vocabulary of 4 foundational upper-level functors (
causes,holds_value,has_state,has_goal) rather than hundreds of domain-specific predicates, the policy does not need to learn new world knowledge during SFT+RLVR—it only learns to route existing latent knowledge into a verifiable relational syntax. Consequently, ~1,500 training episodes are sufficient to reach 97.0%–100% syntax validity and strong cross-domain transfer gains on τ-bench, IFEval, and GPQA while maintaining minimal policy drift (D_KL ≤ 0.0027).