TurnSight assigns credit per tool-call turn, lifting Qwen3-8B tool-reasoning overall avg to 42.02

TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning

Changle Qu, Sunhao Dai, Hengyi Cai, Yuqi Zhou, Xinran Chen, Simon, Jun Xu

cs.CL, cs.AI

2026-08-05

TurnSight does turn-level hindsight self-distillation: it builds teacher views from the agent's own real trajectory at several lookahead horizons, votes on a reliable direction, and modulates RL advantage magnitude without flipping its sign. Qwen3-8B reaches 42.02 overall across three benchmarks, 7.7% over the best baseline.

What problem this solves

When LLMs solve problems with tools (Tool-Integrated Reasoning, TIR), reinforcement learning hits a stubborn wall: credit assignment. By the end of a trajectory you know whether it succeeded, but not which intermediate tool calls helped, which were redundant, and which hurt. Outcome-based RL such as GRPO propagates a single trajectory-level advantage to every action, treating decisions with very different effects as equal.

Existing self-distillation tries to densify the signal, but its teacher's privileged context usually comes from ground-truth answers or reference rollouts that do not match the states the agent actually visits. And token-level supervision misses the structure of a tool interaction: it can hand out conflicting credit within a single turn. TurnSight attacks both. The signal should be dense and rooted in the agent's real path, and it should be scored per turn, not per token.

Method

TurnSight is turn-level hindsight self-distillation, and the design breaks into a few moves:

In one line: it builds supervision from the agent's real trajectory, scores it per turn, and adjusts magnitude without changing direction.

Results

Trained on Qwen3-4B and Qwen3-8B (FTRL dataset, 2,215 problems; MatchTIR as the RL backbone), evaluated on three benchmarks: FTRL (in-domain), BFCL and ToolHop (out-of-domain).

Method (8B)FTRL avgBFCL avgToolHopOverall
MatchTIR (best baseline)42.7833.7840.5439.03
TurnSight46.9237.5641.5842.02

On 8B, overall average climbs from 39.03 to 42.02 (about +3 points absolute, roughly +7.7% relative), with out-of-domain gains too, so it is not overfitting the training distribution. On 4B, overall goes from 34.76 to 37.51.

Ablations (8B, FTRL avg): dropping turn-level aggregation falls to 43.23, group normalization to 43.65, multi-teacher selection to 45.62. All three pull weight. Two notable points: using only tool returns (no ground-truth answer) works best, and among fixed lookaheads one step ahead is strongest while longer horizons hurt. Covering the full trajectory beats first-five-turns (44.56) and last-five-turns (43.04).

Why it matters

Tool use is table stakes for agents, yet most open RL training is still stuck at outcome-level rewards. TurnSight offers a denser signal that needs no ground-truth answer and uses only the agent's own experience, and it plugs into existing GRPO and MatchTIR pipelines (code is open). It is an incremental but real gain: credit moves from trajectory level to turn level, at the cost of extra teacher rollouts with privileged context. If you train agents, it is worth trying on your own long-horizon tool tasks.

Limitations

Terms

Source

Related papers

All paper explainers